{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object/papers/19","list_of":"/task/object","task":"Object","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":19,"pages_in_order":107,"rows_per_page":100,"rows":[1801,1900],"of":10696,"counts":{"archive_papers_tagged":10696,"with_a_code_link":3979,"where_syntology_ran_a_sample":1043,"not_listed_spam_title":0,"listed":10696,"listed_where_code_ran":1043,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":919,"every_run_a_failure_of_syntologys_instrument":124,"listed_with_a_run_with_no_instrument_failure":919,"listed_every_run_a_failure_of_syntologys_instrument":124,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object","prev":"/task/object/papers/18","next":"/task/object/papers/20","papers":[{"url":"/paper/training-free-object-counting-with-prompts","slug":"training-free-object-counting-with-prompts","title":"Training-free Object Counting with Prompts","date":"2023-06-30","arxiv_id":"2307.00038","repositories_listed":1,"syntology":null},{"url":"/paper/egocol-egocentric-camera-pose-estimation-for","slug":"egocol-egocentric-camera-pose-estimation-for","title":"EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023","date":"2023-06-29","arxiv_id":"2306.16606","repositories_listed":1,"syntology":null},{"url":"/paper/multi-source-semantic-graph-based-multimodal","slug":"multi-source-semantic-graph-based-multimodal","title":"Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation","date":"2023-06-29","arxiv_id":"2306.16650","repositories_listed":1,"syntology":null},{"url":"/paper/afpn-asymptotic-feature-pyramid-network-for","slug":"afpn-asymptotic-feature-pyramid-network-for","title":"AFPN: Asymptotic Feature Pyramid Network for Object Detection","date":"2023-06-28","arxiv_id":"2306.15988","repositories_listed":1,"syntology":null},{"url":"/paper/insta-beeer-explicit-error-estimation-and","slug":"insta-beeer-explicit-error-estimation-and","title":"High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement","date":"2023-06-28","arxiv_id":"2306.16132","repositories_listed":1,"syntology":null},{"url":"/paper/transferability-metrics-for-object-detection","slug":"transferability-metrics-for-object-detection","title":"Transferability Metrics for Object Detection","date":"2023-06-27","arxiv_id":"2306.15306","repositories_listed":1,"syntology":null},{"url":"/paper/cst-yolo-a-novel-method-for-blood-cell","slug":"cst-yolo-a-novel-method-for-blood-cell","title":"CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer","date":"2023-06-26","arxiv_id":"2306.14590","repositories_listed":1,"syntology":null},{"url":"/paper/rvt-robotic-view-transformer-for-3d-object","slug":"rvt-robotic-view-transformer-for-3d-object","title":"RVT: Robotic View Transformer for 3D Object Manipulation","date":"2023-06-26","arxiv_id":"2306.14896","repositories_listed":1,"syntology":null},{"url":"/paper/desco-learning-object-recognition-with-rich","slug":"desco-learning-object-recognition-with-rich","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","date":"2023-06-24","arxiv_id":"2306.14060","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/desco-learning-object-recognition-with-rich#ran","syntology_url":"https://syntology.ai/paper/2306.14060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14060"}},"official":null}},{"url":"/paper/openmask3d-open-vocabulary-3d-instance","slug":"openmask3d-open-vocabulary-3d-instance","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","date":"2023-06-23","arxiv_id":"2306.13631","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openmask3d-open-vocabulary-3d-instance#ran","syntology_url":"https://syntology.ai/paper/2306.13631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.13631"}},"official":{"repos":["OpenMask3D/openmask3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shape-constraint-recurrent-flow-for-6d-object-1","slug":"shape-constraint-recurrent-flow-for-6d-object-1","title":"Shape-Constraint Recurrent Flow for 6D Object Pose Estimation","date":"2023-06-23","arxiv_id":"2306.13266","repositories_listed":1,"syntology":null},{"url":"/paper/softgpt-learn-goal-oriented-soft-object","slug":"softgpt-learn-goal-oriented-soft-object","title":"SoftGPT: Learn Goal-oriented Soft Object Manipulation Skills by Generative Pre-trained Heterogeneous Graph Transformer","date":"2023-06-22","arxiv_id":"2306.12677","repositories_listed":1,"syntology":null},{"url":"/paper/crosskd-cross-head-knowledge-distillation-for","slug":"crosskd-cross-head-knowledge-distillation-for","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","date":"2023-06-20","arxiv_id":"2306.11369","repositories_listed":1,"syntology":null},{"url":"/paper/dense-video-object-captioning-from-disjoint","slug":"dense-video-object-captioning-from-disjoint","title":"Dense Video Object Captioning from Disjoint Supervision","date":"2023-06-20","arxiv_id":"2306.11729","repositories_listed":1,"syntology":null},{"url":"/paper/how-can-objects-help-action-recognition-1","slug":"how-can-objects-help-action-recognition-1","title":"How can objects help action recognition?","date":"2023-06-20","arxiv_id":"2306.11726","repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-3d-object-reconstruction-and","slug":"multi-view-3d-object-reconstruction-and","title":"Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Prior","date":"2023-06-17","arxiv_id":"2306.11739","repositories_listed":1,"syntology":null},{"url":"/paper/cad-estate-large-scale-cad-model-annotation","slug":"cad-estate-large-scale-cad-model-annotation","title":"CAD-Estate: Large-scale CAD Model Annotation in RGB Videos","date":"2023-06-15","arxiv_id":"2306.09011","repositories_listed":1,"syntology":null},{"url":"/paper/object-detection-in-hyperspectral-image-via","slug":"object-detection-in-hyperspectral-image-via","title":"Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation","date":"2023-06-14","arxiv_id":"2306.08370","repositories_listed":1,"syntology":null},{"url":"/paper/ocatari-object-centric-atari-2600","slug":"ocatari-object-centric-atari-2600","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","date":"2023-06-14","arxiv_id":"2306.08649","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ocatari-object-centric-atari-2600#ran","syntology_url":"https://syntology.ai/paper/2306.08649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08649"}},"official":{"repos":["k4ntz/oc_atari"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/predict-to-detect-prediction-guided-3d-object","slug":"predict-to-detect-prediction-guided-3d-object","title":"Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images","date":"2023-06-14","arxiv_id":"2306.08528","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-image-captioning-in-top-down-view","slug":"grounded-image-captioning-in-top-down-view","title":"Top-Down Framework for Weakly-supervised Grounded Image Captioning","date":"2023-06-13","arxiv_id":"2306.07490","repositories_listed":1,"syntology":null},{"url":"/paper/referring-camouflaged-object-detection","slug":"referring-camouflaged-object-detection","title":"Referring Camouflaged Object Detection","date":"2023-06-13","arxiv_id":"2306.07532","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/referring-camouflaged-object-detection#ran","syntology_url":"https://syntology.ai/paper/2306.07532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07532"}},"official":{"repos":["zhangxuying1004/refcod"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/compositor-bottom-up-clustering-and-1","slug":"compositor-bottom-up-clustering-and-1","title":"Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation","date":"2023-06-12","arxiv_id":"2306.07404","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/compositor-bottom-up-clustering-and-1#ran","syntology_url":"https://syntology.ai/paper/2306.07404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07404"}},"official":{"repos":["tacju/compositor"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-token-pruning-for-object-detection","slug":"revisiting-token-pruning-for-object-detection","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","date":"2023-06-12","arxiv_id":"2306.07050","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-token-pruning-for-object-detection#ran","syntology_url":"https://syntology.ai/paper/2306.07050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07050"}},"official":{"repos":["uzh-rpg/svit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-robust-sensor-fusion-step-for-3d","slug":"towards-a-robust-sensor-fusion-step-for-3d","title":"Towards a Robust Sensor Fusion Step for 3D Object Detection on Corrupted Data","date":"2023-06-12","arxiv_id":"2306.07344","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-efficacy-of-3d-point-cloud","slug":"on-the-efficacy-of-3d-point-cloud","title":"On the Efficacy of 3D Point Cloud Reinforcement Learning","date":"2023-06-11","arxiv_id":"2306.06799","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-the-efficacy-of-3d-point-cloud#ran","syntology_url":"https://syntology.ai/paper/2306.06799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06799"}},"official":{"repos":["lz1oceani/pointcloud_rl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/aria-digital-twin-a-new-benchmark-dataset-for","slug":"aria-digital-twin-a-new-benchmark-dataset-for","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","date":"2023-06-10","arxiv_id":"2306.06362","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-and-neural-inference-on-lstm-based","slug":"bayesian-and-neural-inference-on-lstm-based","title":"Bayesian and Neural Inference on LSTM-based Object Recognition from Tactile and Kinesthetic Information","date":"2023-06-10","arxiv_id":"2306.06423","repositories_listed":1,"syntology":null},{"url":"/paper/eventclip-adapting-clip-for-event-based","slug":"eventclip-adapting-clip-for-event-based","title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","date":"2023-06-10","arxiv_id":"2306.06354","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eventclip-adapting-clip-for-event-based#ran","syntology_url":"https://syntology.ai/paper/2306.06354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06354"}},"official":{"repos":["Wuziyi616/EventCLIP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ddlp-unsupervised-object-centric-video","slug":"ddlp-unsupervised-object-centric-video","title":"DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles","date":"2023-06-09","arxiv_id":"2306.05957","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ddlp-unsupervised-object-centric-video#ran","syntology_url":"https://syntology.ai/paper/2306.05957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05957"}},"official":{"repos":["taldatech/ddlp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/detzero-rethinking-offboard-3d-object","slug":"detzero-rethinking-offboard-3d-object","title":"DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds","date":"2023-06-09","arxiv_id":"2306.06023","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/detzero-rethinking-offboard-3d-object#ran","syntology_url":"https://syntology.ai/paper/2306.06023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06023"}},"official":{"repos":["pjlab-adg/detzero"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/trajectoryformer-3d-object-tracking","slug":"trajectoryformer-3d-object-tracking","title":"TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses","date":"2023-06-09","arxiv_id":"2306.05888","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trajectoryformer-3d-object-tracking#ran","syntology_url":"https://syntology.ai/paper/2306.05888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05888"}},"official":{"repos":["poodarchu/efg"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exot-exit-aware-object-tracker-for-safe","slug":"exot-exit-aware-object-tracker-for-safe","title":"EXOT: Exit-aware Object Tracker for Safe Robotic Manipulation of Moving Object","date":"2023-06-08","arxiv_id":"2306.05262","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-classifiers-for-open-vocabulary","slug":"multi-modal-classifiers-for-open-vocabulary","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","date":"2023-06-08","arxiv_id":"2306.05493","repositories_listed":1,"syntology":null},{"url":"/paper/object-centric-learning-for-real-world-videos","slug":"object-centric-learning-for-real-world-videos","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","date":"2023-06-07","arxiv_id":"2306.04829","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/object-centric-learning-for-real-world-videos#ran","syntology_url":"https://syntology.ai/paper/2306.04829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04829"}},"official":{"repos":["martius-lab/videosaur"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/g-came-gaussian-class-activation-mapping","slug":"g-came-gaussian-class-activation-mapping","title":"G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors","date":"2023-06-06","arxiv_id":"2306.03400","repositories_listed":1,"syntology":null},{"url":"/paper/human-object-interaction-prediction-in-videos","slug":"human-object-interaction-prediction-in-videos","title":"Human-Object Interaction Prediction in Videos through Gaze Following","date":"2023-06-06","arxiv_id":"2306.03597","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/human-object-interaction-prediction-in-videos#ran","syntology_url":"https://syntology.ai/paper/2306.03597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03597"}},"official":{"repos":["nizhf/hoi-prediction-gaze-transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-the-force-we-can-multi-object-video","slug":"learn-the-force-we-can-multi-object-video","title":"Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation","date":"2023-06-06","arxiv_id":"2306.03988","repositories_listed":1,"syntology":null},{"url":"/paper/mutual-information-regularization-for-weakly","slug":"mutual-information-regularization-for-weakly","title":"Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection","date":"2023-06-06","arxiv_id":"2306.03630","repositories_listed":1,"syntology":null},{"url":"/paper/towards-alleviating-the-object-bias-in-prompt","slug":"towards-alleviating-the-object-bias-in-prompt","title":"Towards Alleviating the Object Bias in Prompt Tuning-based Factual Knowledge Extraction","date":"2023-06-06","arxiv_id":"2306.03378","repositories_listed":1,"syntology":null},{"url":"/paper/cross-drone-transformer-network-for-robust","slug":"cross-drone-transformer-network-for-robust","title":"Cross-Drone Transformer Network for Robust Single Object Tracking","date":"2023-06-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modar-using-motion-forecasting-for-3d-object-1","slug":"modar-using-motion-forecasting-for-3d-object-1","title":"MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences","date":"2023-06-05","arxiv_id":"2306.03206","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/modar-using-motion-forecasting-for-3d-object-1#ran","syntology_url":"https://syntology.ai/paper/2306.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03206"}},"official":null}},{"url":"/paper/reassembling-broken-objects-using-breaking","slug":"reassembling-broken-objects-using-breaking","title":"Reassembling Broken Objects using Breaking Curves","date":"2023-06-05","arxiv_id":"2306.02782","repositories_listed":1,"syntology":null},{"url":"/paper/towards-better-explanations-for-object","slug":"towards-better-explanations-for-object","title":"Towards Better Explanations for Object Detection","date":"2023-06-05","arxiv_id":"2306.02744","repositories_listed":1,"syntology":null},{"url":"/paper/detector-guidance-for-multi-object-text-to","slug":"detector-guidance-for-multi-object-text-to","title":"Detector Guidance for Multi-Object Text-to-Image Generation","date":"2023-06-04","arxiv_id":"2306.02236","repositories_listed":1,"syntology":null},{"url":"/paper/sam3d-zero-shot-3d-object-detection-via","slug":"sam3d-zero-shot-3d-object-detection-via","title":"SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model","date":"2023-06-04","arxiv_id":"2306.02245","repositories_listed":1,"syntology":null},{"url":"/paper/systematic-visual-reasoning-through-object-1","slug":"systematic-visual-reasoning-through-object-1","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","date":"2023-06-04","arxiv_id":"2306.02500","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/systematic-visual-reasoning-through-object-1#ran","syntology_url":"https://syntology.ai/paper/2306.02500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02500"}},"official":{"repos":["shanka123/ocra"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/open-world-text-specified-object-counting","slug":"open-world-text-specified-object-counting","title":"Open-world Text-specified Object Counting","date":"2023-06-02","arxiv_id":"2306.01851","repositories_listed":1,"syntology":null},{"url":"/paper/affinity-based-attention-in-self-supervised","slug":"affinity-based-attention-in-self-supervised","title":"Affinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humans","date":"2023-06-01","arxiv_id":"2306.00294","repositories_listed":1,"syntology":null},{"url":"/paper/agile3d-attention-guided-interactive-multi","slug":"agile3d-attention-guided-interactive-multi","title":"AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation","date":"2023-06-01","arxiv_id":"2306.00977","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agile3d-attention-guided-interactive-multi#ran","syntology_url":"https://syntology.ai/paper/2306.00977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00977"}},"official":null}},{"url":"/paper/graph-switching-dynamical-systems","slug":"graph-switching-dynamical-systems","title":"Graph Switching Dynamical Systems","date":"2023-06-01","arxiv_id":"2306.00370","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":1,"n_ran_checked":2,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":11,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/graph-switching-dynamical-systems#ran","syntology_url":"https://syntology.ai/paper/2306.00370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00370"}},"official":{"repos":["yongtuoliu/graph-switching-dynamical-systems"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/object-pop-up-can-we-infer-3d-objects-and-1","slug":"object-pop-up-can-we-infer-3d-objects-and-1","title":"Object pop-up: Can we infer 3D objects and their poses from human interactions alone?","date":"2023-06-01","arxiv_id":"2306.00777","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":4,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/object-pop-up-can-we-infer-3d-objects-and-1#ran","syntology_url":"https://syntology.ai/paper/2306.00777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00777"}},"official":{"repos":["ptrvilya/object-popup"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/inferring-and-leveraging-parts-from-object-1","slug":"inferring-and-leveraging-parts-from-object-1","title":"Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis","date":"2023-05-31","arxiv_id":"2305.19547","repositories_listed":1,"syntology":null},{"url":"/paper/point-gcc-universal-self-supervised-3d-scene","slug":"point-gcc-universal-self-supervised-3d-scene","title":"Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast","date":"2023-05-31","arxiv_id":"2305.19623","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-vision-transformers-for-3d","slug":"self-supervised-vision-transformers-for-3d","title":"Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects","date":"2023-05-31","arxiv_id":"2306.00129","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-queried-object-detection-in-the","slug":"multi-modal-queried-object-detection-in-the","title":"Multi-modal Queried Object Detection in the Wild","date":"2023-05-30","arxiv_id":"2305.18980","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-queried-object-detection-in-the#ran","syntology_url":"https://syntology.ai/paper/2305.18980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18980"}},"official":{"repos":["yifanxu74/mq-det"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-method-for-studying-semantic-construal-in","slug":"a-method-for-studying-semantic-construal-in","title":"A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces","date":"2023-05-29","arxiv_id":"2305.18598","repositories_listed":1,"syntology":null},{"url":"/paper/camodiffusion-camouflaged-object-detection","slug":"camodiffusion-camouflaged-object-detection","title":"CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models","date":"2023-05-29","arxiv_id":"2305.17932","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-object-detection-with-multimodal","slug":"contextual-object-detection-with-multimodal","title":"Contextual Object Detection with Multimodal Large Language Models","date":"2023-05-29","arxiv_id":"2305.18279","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contextual-object-detection-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2305.18279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18279"}},"official":{"repos":["yuhangzang/contextdet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vcvw-3d-a-virtual-construction-vehicles-and","slug":"vcvw-3d-a-virtual-construction-vehicles-and","title":"VCVW-3D: A Virtual Construction Vehicles and Workers Dataset with 3D Annotations","date":"2023-05-29","arxiv_id":"2305.17927","repositories_listed":1,"syntology":null},{"url":"/paper/lighting-and-rotation-invariant-real-time","slug":"lighting-and-rotation-invariant-real-time","title":"Lighting and Rotation Invariant Real-time Vehicle Wheel Detector based on YOLOv5","date":"2023-05-28","arxiv_id":"2305.17785","repositories_listed":1,"syntology":null},{"url":"/paper/nero-neural-geometry-and-brdf-reconstruction","slug":"nero-neural-geometry-and-brdf-reconstruction","title":"NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images","date":"2023-05-27","arxiv_id":"2305.17398","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nero-neural-geometry-and-brdf-reconstruction#ran","syntology_url":"https://syntology.ai/paper/2305.17398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17398"}},"official":{"repos":["liuyuan-pal/nero"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-importance-of-backbone-to-the","slug":"on-the-importance-of-backbone-to-the","title":"On the Importance of Backbone to the Adversarial Robustness of Object Detectors","date":"2023-05-27","arxiv_id":"2305.17438","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-pose-estimation-using-implicit","slug":"generalizable-pose-estimation-using-implicit","title":"Generalizable Pose Estimation Using Implicit Scene Representations","date":"2023-05-26","arxiv_id":"2305.17252","repositories_listed":1,"syntology":null},{"url":"/paper/soc-semantic-assisted-object-cluster-for","slug":"soc-semantic-assisted-object-cluster-for","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","date":"2023-05-26","arxiv_id":"2305.17011","repositories_listed":1,"syntology":null},{"url":"/paper/camera-incremental-object-re-identification","slug":"camera-incremental-object-re-identification","title":"Camera-Incremental Object Re-Identification with Identity Knowledge Evolution","date":"2023-05-25","arxiv_id":"2305.15909","repositories_listed":1,"syntology":null},{"url":"/paper/commonscenes-generating-commonsense-3d-indoor","slug":"commonscenes-generating-commonsense-3d-indoor","title":"CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion","date":"2023-05-25","arxiv_id":"2305.16283","repositories_listed":1,"syntology":{"n":25,"n_ran":11,"n_constructed":6,"n_ran_checked":9,"n_instrument":2,"n_unverified":14,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":25,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/commonscenes-generating-commonsense-3d-indoor#ran","syntology_url":"https://syntology.ai/paper/2305.16283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16283"}},"official":{"repos":["ymxlzgy/commonscenes"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":6,"n_ran_no_instrument_failure":9,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/confronting-ambiguity-in-6d-object-pose","slug":"confronting-ambiguity-in-6d-object-pose","title":"Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)","date":"2023-05-25","arxiv_id":"2305.15873","repositories_listed":1,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/confronting-ambiguity-in-6d-object-pose#ran","syntology_url":"https://syntology.ai/paper/2305.15873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15873"}},"official":{"repos":["Ending2015a/liepose-diffusion"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/guided-attention-for-next-active-object-ego4d","slug":"guided-attention-for-next-active-object-ego4d","title":"Guided Attention for Next Active Object @ EGO4D STA Challenge","date":"2023-05-25","arxiv_id":"2305.16066","repositories_listed":1,"syntology":null},{"url":"/paper/learning-occupancy-for-monocular-3d-object","slug":"learning-occupancy-for-monocular-3d-object","title":"Learning Occupancy for Monocular 3D Object Detection","date":"2023-05-25","arxiv_id":"2305.15694","repositories_listed":1,"syntology":null},{"url":"/paper/nap-neural-3d-articulation-prior","slug":"nap-neural-3d-articulation-prior","title":"NAP: Neural 3D Articulation Prior","date":"2023-05-25","arxiv_id":"2305.16315","repositories_listed":1,"syntology":null},{"url":"/paper/pope-6-dof-promptable-pose-estimation-of-any","slug":"pope-6-dof-promptable-pose-estimation-of-any","title":"POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference","date":"2023-05-25","arxiv_id":"2305.15727","repositories_listed":1,"syntology":null},{"url":"/paper/referred-by-multi-modality-a-unified-temporal","slug":"referred-by-multi-modality-a-unified-temporal","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","date":"2023-05-25","arxiv_id":"2305.16318","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-training-of-complex-valued-1","slug":"contrastive-training-of-complex-valued-1","title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","date":"2023-05-24","arxiv_id":"2305.15001","repositories_listed":1,"syntology":{"n":38,"n_ran":29,"n_constructed":5,"n_ran_checked":12,"n_instrument":17,"n_unverified":9,"n_honours":4,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"29 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 1 violated, 7 with no contract checked; 17 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/contrastive-training-of-complex-valued-1#ran","syntology_url":"https://syntology.ai/paper/2305.15001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15001"}},"official":{"repos":["agopal42/ctcae"],"state":"official (archive's flag): 29 ran","n_ran":29,"n_constructed":5,"n_ran_no_instrument_failure":12,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/dc-net-divide-and-conquer-for-salient-object","slug":"dc-net-divide-and-conquer-for-salient-object","title":"DC-Net: Divide-and-Conquer for Salient Object Detection","date":"2023-05-24","arxiv_id":"2305.14955","repositories_listed":1,"syntology":null},{"url":"/paper/realistically-distributing-object-placements","slug":"realistically-distributing-object-placements","title":"Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models","date":"2023-05-24","arxiv_id":"2305.14621","repositories_listed":1,"syntology":null},{"url":"/paper/robust-3d-aware-object-classification-via","slug":"robust-3d-aware-object-classification-via","title":"NOVUM: Neural Object Volumes for Robust Object Classification","date":"2023-05-24","arxiv_id":"2305.14668","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-and-long-tailed-object","slug":"semi-supervised-and-long-tailed-object","title":"Semi-Supervised and Long-Tailed Object Detection with CascadeMatch","date":"2023-05-24","arxiv_id":"2305.14813","repositories_listed":1,"syntology":null},{"url":"/paper/text-encoders-are-performance-bottlenecks-in","slug":"text-encoders-are-performance-bottlenecks-in","title":"Text encoders bottleneck compositionality in contrastive vision-language models","date":"2023-05-24","arxiv_id":"2305.14897","repositories_listed":1,"syntology":null},{"url":"/paper/what-can-generic-neural-networks-learn-from-a","slug":"what-can-generic-neural-networks-learn-from-a","title":"Learning high-level visual representations from a child's perspective without strong inductive biases","date":"2023-05-24","arxiv_id":"2305.15372","repositories_listed":1,"syntology":null},{"url":"/paper/detgpt-detect-what-you-need-via-reasoning","slug":"detgpt-detect-what-you-need-via-reasoning","title":"DetGPT: Detect What You Need via Reasoning","date":"2023-05-23","arxiv_id":"2305.14167","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/detgpt-detect-what-you-need-via-reasoning#ran","syntology_url":"https://syntology.ai/paper/2305.14167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14167"}},"official":null}},{"url":"/paper/learning-remote-sensing-object-detection-with","slug":"learning-remote-sensing-object-detection-with","title":"Learning Remote Sensing Object Detection with Single Point Supervision","date":"2023-05-23","arxiv_id":"2305.14141","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-next-active-object-based-egocentric","slug":"enhancing-next-active-object-based-egocentric","title":"Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention","date":"2023-05-22","arxiv_id":"2305.12953","repositories_listed":1,"syntology":null},{"url":"/paper/uvosam-a-mask-free-paradigm-for-unsupervised","slug":"uvosam-a-mask-free-paradigm-for-unsupervised","title":"UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model","date":"2023-05-22","arxiv_id":"2305.12659","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-referring-expression-segmentation","slug":"advancing-referring-expression-segmentation","title":"Advancing Referring Expression Segmentation Beyond Single Image","date":"2023-05-21","arxiv_id":"2305.12452","repositories_listed":1,"syntology":null},{"url":"/paper/yolov3-with-spatial-pyramid-pooling-for","slug":"yolov3-with-spatial-pyramid-pooling-for","title":"YOLOv3 with Spatial Pyramid Pooling for Object Detection with Unmanned Aerial Vehicles","date":"2023-05-21","arxiv_id":"2305.12344","repositories_listed":1,"syntology":null},{"url":"/paper/when-sam-meets-shadow-detection","slug":"when-sam-meets-shadow-detection","title":"When SAM Meets Shadow Detection","date":"2023-05-19","arxiv_id":"2305.11513","repositories_listed":1,"syntology":null},{"url":"/paper/object-segmentation-by-mining-cross-modal","slug":"object-segmentation-by-mining-cross-modal","title":"Object Segmentation by Mining Cross-Modal Semantics","date":"2023-05-17","arxiv_id":"2305.10469","repositories_listed":1,"syntology":null},{"url":"/paper/or-nerf-object-removing-from-3d-scenes-guided","slug":"or-nerf-object-removing-from-3d-scenes-guided","title":"OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields","date":"2023-05-17","arxiv_id":"2305.10503","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-boundary-discontinuity-problem-for","slug":"rethinking-boundary-discontinuity-problem-for","title":"Rethinking Boundary Discontinuity Problem for Oriented Object Detection","date":"2023-05-17","arxiv_id":"2305.10061","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-simultaneous-multi-object-3d-shape","slug":"real-time-simultaneous-multi-object-3d-shape","title":"Real-time Simultaneous Multi-Object 3D Shape Reconstruction, 6DoF Pose Estimation and Dense Grasp Prediction","date":"2023-05-16","arxiv_id":"2305.09510","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-3d-object-interaction-from-a","slug":"understanding-3d-object-interaction-from-a","title":"Understanding 3D Object Interaction from a Single Image","date":"2023-05-16","arxiv_id":"2305.09664","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-domain-gap-self-supervised-3d","slug":"bridging-the-domain-gap-self-supervised-3d","title":"Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models","date":"2023-05-15","arxiv_id":"2305.08776","repositories_listed":1,"syntology":null},{"url":"/paper/clip-count-towards-text-guided-zero-shot","slug":"clip-count-towards-text-guided-zero-shot","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","date":"2023-05-12","arxiv_id":"2305.07304","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-count-towards-text-guided-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2305.07304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07304"}},"official":{"repos":["songrise/clip-count"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/imaginator-pre-trained-image-text-joint","slug":"imaginator-pre-trained-image-text-joint","title":"IMAGINATOR: Pre-Trained Image+Text Joint Embeddings using Word-Level Grounding of Images","date":"2023-05-12","arxiv_id":"2305.10438","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-3d-object-detection-by-box","slug":"multi-modal-3d-object-detection-by-box","title":"Multi-Modal 3D Object Detection by Box Matching","date":"2023-05-12","arxiv_id":"2305.07713","repositories_listed":1,"syntology":null},{"url":"/paper/rhino-rotated-detr-with-dynamic-denoising-via","slug":"rhino-rotated-detr-with-dynamic-denoising-via","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","date":"2023-05-12","arxiv_id":"2305.07598","repositories_listed":1,"syntology":null},{"url":"/paper/ssd-monodtr-supervised-scale-constrained","slug":"ssd-monodtr-supervised-scale-constrained","title":"SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection","date":"2023-05-12","arxiv_id":"2305.07270","repositories_listed":1,"syntology":null},{"url":"/paper/saliendet-a-saliency-based-feature","slug":"saliendet-a-saliency-based-feature","title":"SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving","date":"2023-05-11","arxiv_id":"2305.06940","repositories_listed":1,"syntology":null},{"url":"/paper/multi-object-self-supervised-depth-denoising","slug":"multi-object-self-supervised-depth-denoising","title":"Multi-Object Self-Supervised Depth Denoising","date":"2023-05-09","arxiv_id":"2305.05778","repositories_listed":1,"syntology":null}],"record_sha256":"98320dd31b578eebff54f31f922b2cc3075327e05ab0503be1271c6ca74d5999","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}