{"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/scene-understanding/papers/5","list_of":"/task/scene-understanding","task":"Scene Understanding","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":5,"pages_in_order":18,"rows_per_page":100,"rows":[401,500],"of":1723,"counts":{"archive_papers_tagged":1723,"with_a_code_link":720,"where_syntology_ran_a_sample":208,"not_listed_spam_title":0,"listed":1723,"listed_where_code_ran":208,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":182,"every_run_a_failure_of_syntologys_instrument":26,"listed_with_a_run_with_no_instrument_failure":182,"listed_every_run_a_failure_of_syntologys_instrument":26,"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/scene-understanding","prev":"/task/scene-understanding/papers/4","next":"/task/scene-understanding/papers/6","papers":[{"url":"/paper/fine-grained-is-too-coarse-a-novel-data","slug":"fine-grained-is-too-coarse-a-novel-data","title":"Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation","date":"2023-05-30","arxiv_id":"2305.18668","repositories_listed":1,"syntology":null},{"url":"/paper/multi-scale-attention-for-audio-question","slug":"multi-scale-attention-for-audio-question","title":"Multi-Scale Attention for Audio Question Answering","date":"2023-05-29","arxiv_id":"2305.17993","repositories_listed":1,"syntology":null},{"url":"/paper/target-aware-spatio-temporal-reasoning-via","slug":"target-aware-spatio-temporal-reasoning-via","title":"Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual Scenarios","date":"2023-05-21","arxiv_id":"2305.12397","repositories_listed":1,"syntology":null},{"url":"/paper/generating-visual-spatial-description-via","slug":"generating-visual-spatial-description-via","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","date":"2023-05-19","arxiv_id":"2305.11768","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 2 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) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/generating-visual-spatial-description-via#ran","syntology_url":"https://syntology.ai/paper/2305.11768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11768"}},"official":{"repos":["zhaoyucs/vsd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/textslam-visual-slam-with-semantic-planar","slug":"textslam-visual-slam-with-semantic-planar","title":"TextSLAM: Visual SLAM with Semantic Planar Text Features","date":"2023-05-17","arxiv_id":"2305.10029","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/cross-modality-time-variant-relation-learning","slug":"cross-modality-time-variant-relation-learning","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","date":"2023-05-15","arxiv_id":"2305.08522","repositories_listed":1,"syntology":null},{"url":"/paper/taskprompter-spatial-channel-multi-task","slug":"taskprompter-spatial-channel-multi-task","title":"TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding","date":"2023-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/object-centric-voxelization-of-dynamic-scenes","slug":"object-centric-voxelization-of-dynamic-scenes","title":"DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization","date":"2023-04-30","arxiv_id":"2305.00393","repositories_listed":1,"syntology":null},{"url":"/paper/a-review-of-panoptic-segmentation-for-mobile","slug":"a-review-of-panoptic-segmentation-for-mobile","title":"A Review of Panoptic Segmentation for Mobile Mapping Point Clouds","date":"2023-04-27","arxiv_id":"2304.13980","repositories_listed":1,"syntology":null},{"url":"/paper/indiscernible-object-counting-in-underwater","slug":"indiscernible-object-counting-in-underwater","title":"RGB-D Indiscernible Object Counting in Underwater Scenes","date":"2023-04-23","arxiv_id":"2304.11677","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-from-3d-to-bird-s-eye","slug":"knowledge-distillation-from-3d-to-bird-s-eye","title":"Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation","date":"2023-04-22","arxiv_id":"2304.11393","repositories_listed":1,"syntology":null},{"url":"/paper/advances-in-deep-concealed-scene","slug":"advances-in-deep-concealed-scene","title":"Advances in Deep Concealed Scene Understanding","date":"2023-04-21","arxiv_id":"2304.11234","repositories_listed":1,"syntology":null},{"url":"/paper/rs2g-data-driven-scene-graph-extraction-and","slug":"rs2g-data-driven-scene-graph-extraction-and","title":"RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding","date":"2023-04-17","arxiv_id":"2304.08600","repositories_listed":1,"syntology":null},{"url":"/paper/strap-structured-object-affordance","slug":"strap-structured-object-affordance","title":"STRAP: Structured Object Affordance Segmentation with Point Supervision","date":"2023-04-17","arxiv_id":"2304.08492","repositories_listed":1,"syntology":null},{"url":"/paper/viplo-vision-transformer-based-pose","slug":"viplo-vision-transformer-based-pose","title":"ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection","date":"2023-04-17","arxiv_id":"2304.08114","repositories_listed":1,"syntology":null},{"url":"/paper/topology-reasoning-for-driving-scenes","slug":"topology-reasoning-for-driving-scenes","title":"Graph-based Topology Reasoning for Driving Scenes","date":"2023-04-11","arxiv_id":"2304.05277","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":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) · 0 unverified","sample_list":"/paper/topology-reasoning-for-driving-scenes#ran","syntology_url":"https://syntology.ai/paper/2304.05277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05277"}},"official":{"repos":["opendrivelab/toponet"],"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/semantic-segmentation-with-high-inference","slug":"semantic-segmentation-with-high-inference","title":"Semantic Segmentation with High Inference Speed in Off-Road Environments","date":"2023-04-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fredom-fairness-domain-adaptation-approach-to","slug":"fredom-fairness-domain-adaptation-approach-to","title":"FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding","date":"2023-04-04","arxiv_id":"2304.02135","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/fredom-fairness-domain-adaptation-approach-to#ran","syntology_url":"https://syntology.ai/paper/2304.02135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02135"}},"official":{"repos":["uark-cviu/fredom"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/regionplc-regional-point-language-contrastive","slug":"regionplc-regional-point-language-contrastive","title":"RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding","date":"2023-04-03","arxiv_id":"2304.00962","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/regionplc-regional-point-language-contrastive#ran","syntology_url":"https://syntology.ai/paper/2304.00962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00962"}},"official":{"repos":["cvmi-lab/pla"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/complementary-random-masking-for-rgb-thermal","slug":"complementary-random-masking-for-rgb-thermal","title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","date":"2023-03-30","arxiv_id":"2303.17386","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/complementary-random-masking-for-rgb-thermal#ran","syntology_url":"https://syntology.ai/paper/2303.17386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17386"}},"official":{"repos":["UkcheolShin/CRM_RGBTSeg"],"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/dpf-learning-dense-prediction-fields-with","slug":"dpf-learning-dense-prediction-fields-with","title":"DPF: Learning Dense Prediction Fields with Weak Supervision","date":"2023-03-29","arxiv_id":"2303.16890","repositories_listed":1,"syntology":{"n":34,"n_ran":23,"n_constructed":13,"n_ran_checked":13,"n_instrument":10,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":34,"phrase":"23 ran (of which 13 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/dpf-learning-dense-prediction-fields-with#ran","syntology_url":"https://syntology.ai/paper/2303.16890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16890"}},"official":{"repos":["cxx226/dpf"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":13,"n_ran_no_instrument_failure":13,"n_unverified":11,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/hilo-exploiting-high-low-frequency-relations","slug":"hilo-exploiting-high-low-frequency-relations","title":"HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation","date":"2023-03-28","arxiv_id":"2303.15994","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-semantic-segmentation-using","slug":"real-time-semantic-segmentation-using","title":"Real-Time Semantic Segmentation using Hyperspectral Images for Mapping Unstructured and Unknown Environments","date":"2023-03-27","arxiv_id":"2303.15623","repositories_listed":1,"syntology":null},{"url":"/paper/one-thing-one-click-self-training-for-weakly","slug":"one-thing-one-click-self-training-for-weakly","title":"You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding","date":"2023-03-26","arxiv_id":"2303.14727","repositories_listed":1,"syntology":null},{"url":"/paper/ovenet-offset-vector-network-for-semantic","slug":"ovenet-offset-vector-network-for-semantic","title":"OVeNet: Offset Vector Network for Semantic Segmentation","date":"2023-03-25","arxiv_id":"2303.14516","repositories_listed":1,"syntology":null},{"url":"/paper/viewpoint-equivariance-for-multi-view-3d","slug":"viewpoint-equivariance-for-multi-view-3d","title":"Viewpoint Equivariance for Multi-View 3D Object Detection","date":"2023-03-25","arxiv_id":"2303.14548","repositories_listed":1,"syntology":null},{"url":"/paper/self-distillation-for-surgical-action","slug":"self-distillation-for-surgical-action","title":"Self-distillation for surgical action recognition","date":"2023-03-22","arxiv_id":"2303.12915","repositories_listed":1,"syntology":null},{"url":"/paper/clip-goes-3d-leveraging-prompt-tuning-for","slug":"clip-goes-3d-leveraging-prompt-tuning-for","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","date":"2023-03-20","arxiv_id":"2303.11313","repositories_listed":1,"syntology":null},{"url":"/paper/long-term-indoor-localization-with-metric","slug":"long-term-indoor-localization-with-metric","title":"Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor Localization","date":"2023-03-20","arxiv_id":"2303.10959","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-segmentation-of-surgical","slug":"semantic-segmentation-of-surgical","title":"Semantic segmentation of surgical hyperspectral images under geometric domain shifts","date":"2023-03-20","arxiv_id":"2303.10972","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-computation-sharing-for-multi-task","slug":"efficient-computation-sharing-for-multi-task","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","date":"2023-03-16","arxiv_id":"2303.09663","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-computation-sharing-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2303.09663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09663"}},"official":{"repos":["sarashoouri/efficientmtl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/penet-a-joint-panoptic-edge-detection-network","slug":"penet-a-joint-panoptic-edge-detection-network","title":"PENet: A Joint Panoptic Edge Detection Network","date":"2023-03-15","arxiv_id":"2303.08848","repositories_listed":1,"syntology":null},{"url":"/paper/pimae-point-cloud-and-image-interactive","slug":"pimae-point-cloud-and-image-interactive","title":"PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection","date":"2023-03-14","arxiv_id":"2303.08129","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/pimae-point-cloud-and-image-interactive#ran","syntology_url":"https://syntology.ai/paper/2303.08129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08129"}},"official":{"repos":["blvlab/pimae"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fac-3d-representation-learning-via-foreground","slug":"fac-3d-representation-learning-via-foreground","title":"Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast","date":"2023-03-11","arxiv_id":"2303.06388","repositories_listed":1,"syntology":null},{"url":"/paper/traffic-scene-parsing-through-the-tsp6k","slug":"traffic-scene-parsing-through-the-tsp6k","title":"Traffic Scene Parsing through the TSP6K Dataset","date":"2023-03-06","arxiv_id":"2303.02835","repositories_listed":1,"syntology":null},{"url":"/paper/vtqa-visual-text-question-answering-via","slug":"vtqa-visual-text-question-answering-via","title":"VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning","date":"2023-03-05","arxiv_id":"2303.02635","repositories_listed":1,"syntology":null},{"url":"/paper/cekd-cross-modal-edge-privileged-knowledge","slug":"cekd-cross-modal-edge-privileged-knowledge","title":"CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images","date":"2023-02-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-event-based-vision-a","slug":"deep-learning-for-event-based-vision-a","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","date":"2023-02-17","arxiv_id":"2302.08890","repositories_listed":1,"syntology":null},{"url":"/paper/3d-neural-embedding-likelihood-for-robust-sim","slug":"3d-neural-embedding-likelihood-for-robust-sim","title":"3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation","date":"2023-02-07","arxiv_id":"2302.03744","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/3d-neural-embedding-likelihood-for-robust-sim#ran","syntology_url":"https://syntology.ai/paper/2302.03744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03744"}},"official":{"repos":["deepmind/threednel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ovarnet-towards-open-vocabulary-object","slug":"ovarnet-towards-open-vocabulary-object","title":"OvarNet: Towards Open-vocabulary Object Attribute Recognition","date":"2023-01-23","arxiv_id":"2301.09506","repositories_listed":1,"syntology":null},{"url":"/paper/unleash-the-potential-of-image-branch-for-1","slug":"unleash-the-potential-of-image-branch-for-1","title":"Unleash the Potential of Image Branch for Cross-modal 3D Object Detection","date":"2023-01-22","arxiv_id":"2301.09077","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/unleash-the-potential-of-image-branch-for-1#ran","syntology_url":"https://syntology.ai/paper/2301.09077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.09077"}},"official":{"repos":["eaphan/upidet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-inexact-graph-matching-on-top-of","slug":"model-based-inexact-graph-matching-on-top-of","title":"Model-based inexact graph matching on top of CNNs for semantic scene understanding","date":"2023-01-18","arxiv_id":"2301.07468","repositories_listed":1,"syntology":null},{"url":"/paper/clip2scene-towards-label-efficient-3d-scene","slug":"clip2scene-towards-label-efficient-3d-scene","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","date":"2023-01-12","arxiv_id":"2301.04926","repositories_listed":1,"syntology":null},{"url":"/paper/neural-radiance-field-codebooks","slug":"neural-radiance-field-codebooks","title":"Neural Radiance Field Codebooks","date":"2023-01-10","arxiv_id":"2301.04101","repositories_listed":1,"syntology":null},{"url":"/paper/uni-3d-a-universal-model-for-panoptic-3d","slug":"uni-3d-a-universal-model-for-panoptic-3d","title":"Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-pre-training-for-3d-point","slug":"self-supervised-pre-training-for-3d-point","title":"PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation","date":"2022-12-29","arxiv_id":"2212.14197","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-aware-paced-curriculum-learning-by","slug":"confidence-aware-paced-curriculum-learning-by","title":"Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding","date":"2022-12-22","arxiv_id":"2212.11511","repositories_listed":1,"syntology":null},{"url":"/paper/meteor-guided-divergence-for-video-captioning","slug":"meteor-guided-divergence-for-video-captioning","title":"METEOR Guided Divergence for Video Captioning","date":"2022-12-20","arxiv_id":"2212.10690","repositories_listed":1,"syntology":null},{"url":"/paper/learning-object-level-point-augmentor-for","slug":"learning-object-level-point-augmentor-for","title":"Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection","date":"2022-12-19","arxiv_id":"2212.09273","repositories_listed":1,"syntology":null},{"url":"/paper/panoptic-lifting-for-3d-scene-understanding","slug":"panoptic-lifting-for-3d-scene-understanding","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","date":"2022-12-19","arxiv_id":"2212.09802","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-integration-of-3d-features-to","slug":"lightweight-integration-of-3d-features-to","title":"Lightweight integration of 3D features to improve 2D image segmentation","date":"2022-12-16","arxiv_id":"2212.08334","repositories_listed":1,"syntology":null},{"url":"/paper/towards-holistic-surgical-scene-understanding","slug":"towards-holistic-surgical-scene-understanding","title":"Towards Holistic Surgical Scene Understanding","date":"2022-12-08","arxiv_id":"2212.04582","repositories_listed":1,"syntology":null},{"url":"/paper/lwsis-lidar-guided-weakly-supervised-instance","slug":"lwsis-lidar-guided-weakly-supervised-instance","title":"LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving","date":"2022-12-07","arxiv_id":"2212.03504","repositories_listed":1,"syntology":null},{"url":"/paper/towards-scene-understanding-for-autonomous","slug":"towards-scene-understanding-for-autonomous","title":"Towards Scene Understanding for Autonomous Operations on Airport Aprons","date":"2022-12-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-driven-open-vocabulary-3d-scene","slug":"language-driven-open-vocabulary-3d-scene","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","date":"2022-11-29","arxiv_id":"2211.16312","repositories_listed":1,"syntology":null},{"url":"/paper/openscene-3d-scene-understanding-with-open","slug":"openscene-3d-scene-understanding-with-open","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","date":"2022-11-28","arxiv_id":"2211.15654","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"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) · 2 unverified","sample_list":"/paper/openscene-3d-scene-understanding-with-open#ran","syntology_url":"https://syntology.ai/paper/2211.15654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15654"}},"official":null}},{"url":"/paper/task-aware-asynchronous-multi-task-model-with","slug":"task-aware-asynchronous-multi-task-model-with","title":"Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene Understanding","date":"2022-11-28","arxiv_id":"2211.15327","repositories_listed":1,"syntology":null},{"url":"/paper/language-assisted-3d-feature-learning-for","slug":"language-assisted-3d-feature-learning-for","title":"Language-Assisted 3D Feature Learning for Semantic Scene Understanding","date":"2022-11-25","arxiv_id":"2211.14091","repositories_listed":1,"syntology":null},{"url":"/paper/computational-optics-meet-domain-adaptation","slug":"computational-optics-meet-domain-adaptation","title":"Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrations","date":"2022-11-21","arxiv_id":"2211.11257","repositories_listed":1,"syntology":null},{"url":"/paper/doubly-contrastive-end-to-end-semantic","slug":"doubly-contrastive-end-to-end-semantic","title":"Doubly Contrastive End-to-End Semantic Segmentation for Autonomous Driving under Adverse Weather","date":"2022-11-21","arxiv_id":"2211.11131","repositories_listed":1,"syntology":null},{"url":"/paper/bevdistill-cross-modal-bev-distillation-for","slug":"bevdistill-cross-modal-bev-distillation-for","title":"BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection","date":"2022-11-17","arxiv_id":"2211.09386","repositories_listed":1,"syntology":null},{"url":"/paper/flowgrad-using-motion-for-visual-sound-source","slug":"flowgrad-using-motion-for-visual-sound-source","title":"FlowGrad: Using Motion for Visual Sound Source Localization","date":"2022-11-15","arxiv_id":"2211.08367","repositories_listed":1,"syntology":null},{"url":"/paper/visually-grounded-vqa-by-lattice-based","slug":"visually-grounded-vqa-by-lattice-based","title":"Visually Grounded VQA by Lattice-based Retrieval","date":"2022-11-15","arxiv_id":"2211.08086","repositories_listed":1,"syntology":null},{"url":"/paper/rgb-t-semantic-segmentation-with-location","slug":"rgb-t-semantic-segmentation-with-location","title":"RGB-T Semantic Segmentation with Location, Activation, and Sharpening","date":"2022-10-26","arxiv_id":"2210.14530","repositories_listed":1,"syntology":null},{"url":"/paper/sim-to-real-via-sim-to-seg-end-to-end-off","slug":"sim-to-real-via-sim-to-seg-end-to-end-off","title":"Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data","date":"2022-10-25","arxiv_id":"2210.14721","repositories_listed":1,"syntology":null},{"url":"/paper/pareto-manifold-learning-tackling-multiple","slug":"pareto-manifold-learning-tackling-multiple","title":"Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models","date":"2022-10-18","arxiv_id":"2210.09759","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/pareto-manifold-learning-tackling-multiple#ran","syntology_url":"https://syntology.ai/paper/2210.09759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09759"}},"official":{"repos":["nik-dim/pamal"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sqa3d-situated-question-answering-in-3d","slug":"sqa3d-situated-question-answering-in-3d","title":"SQA3D: Situated Question Answering in 3D Scenes","date":"2022-10-14","arxiv_id":"2210.07474","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":6,"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 6 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/sqa3d-situated-question-answering-in-3d#ran","syntology_url":"https://syntology.ai/paper/2210.07474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07474"}},"official":{"repos":["SilongYong/SQA3D"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-aware-lidar-panoptic-segmentation","slug":"uncertainty-aware-lidar-panoptic-segmentation","title":"Uncertainty-aware LiDAR Panoptic Segmentation","date":"2022-10-10","arxiv_id":"2210.04472","repositories_listed":1,"syntology":null},{"url":"/paper/flow-based-gan-for-3d-point-cloud-generation","slug":"flow-based-gan-for-3d-point-cloud-generation","title":"Flow-based GAN for 3D Point Cloud Generation from a Single Image","date":"2022-10-08","arxiv_id":"2210.04072","repositories_listed":1,"syntology":null},{"url":"/paper/image-masking-for-robust-self-supervised","slug":"image-masking-for-robust-self-supervised","title":"Image Masking for Robust Self-Supervised Monocular Depth Estimation","date":"2022-10-05","arxiv_id":"2210.02357","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/image-masking-for-robust-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2210.02357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02357"}},"official":{"repos":["neurai-lab/mimdepth"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/fredsnet-joint-monocular-depth-and-semantic","slug":"fredsnet-joint-monocular-depth-and-semantic","title":"FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions","date":"2022-10-04","arxiv_id":"2210.01595","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-driven-active-vision-for-implicit","slug":"uncertainty-driven-active-vision-for-implicit","title":"Uncertainty-Driven Active Vision for Implicit Scene Reconstruction","date":"2022-10-03","arxiv_id":"2210.00978","repositories_listed":1,"syntology":null},{"url":"/paper/holistic-segmentation","slug":"holistic-segmentation","title":"Segmenting Known Objects and Unseen Unknowns without Prior Knowledge","date":"2022-09-12","arxiv_id":"2209.05407","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-robot-3d","slug":"leveraging-large-language-models-for-robot-3d","title":"Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding","date":"2022-09-12","arxiv_id":"2209.05629","repositories_listed":1,"syntology":null},{"url":"/paper/massmind-massachusetts-maritime-infrared","slug":"massmind-massachusetts-maritime-infrared","title":"MassMIND: Massachusetts Maritime INfrared Dataset","date":"2022-09-09","arxiv_id":"2209.04097","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-cross-attention-based-multi-task","slug":"sequential-cross-attention-based-multi-task","title":"Sequential Cross Attention Based Multi-task Learning","date":"2022-09-06","arxiv_id":"2209.02518","repositories_listed":1,"syntology":null},{"url":"/paper/semsegdepth-a-combined-model-for-semantic","slug":"semsegdepth-a-combined-model-for-semantic","title":"SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion","date":"2022-09-01","arxiv_id":"2209.00381","repositories_listed":1,"syntology":null},{"url":"/paper/rwseg-cross-graph-competing-random-walks-for","slug":"rwseg-cross-graph-competing-random-walks-for","title":"Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision","date":"2022-08-10","arxiv_id":"2208.05110","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-segmentation-assisted-instance","slug":"semantic-segmentation-assisted-instance","title":"Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation","date":"2022-08-09","arxiv_id":"2208.04766","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantic-segmentation-assisted-instance#ran","syntology_url":"https://syntology.ai/paper/2208.04766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.04766"}},"official":{"repos":["isunchy/3d_instance_segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tag-boosting-text-vqa-via-text-aware-visual","slug":"tag-boosting-text-vqa-via-text-aware-visual","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","date":"2022-08-03","arxiv_id":"2208.01813","repositories_listed":1,"syntology":null},{"url":"/paper/monteboxfinder-detecting-and-filtering","slug":"monteboxfinder-detecting-and-filtering","title":"MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud","date":"2022-07-28","arxiv_id":"2207.14268","repositories_listed":1,"syntology":null},{"url":"/paper/safety-enhanced-autonomous-driving-using-1","slug":"safety-enhanced-autonomous-driving-using-1","title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","date":"2022-07-28","arxiv_id":"2207.14024","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/safety-enhanced-autonomous-driving-using-1#ran","syntology_url":"https://syntology.ai/paper/2207.14024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.14024"}},"official":{"repos":["opendilab/InterFuser"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/semantic-abstraction-open-world-3d-scene","slug":"semantic-abstraction-open-world-3d-scene","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","date":"2022-07-23","arxiv_id":"2207.11514","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/semantic-abstraction-open-world-3d-scene#ran","syntology_url":"https://syntology.ai/paper/2207.11514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11514"}},"official":{"repos":["columbia-ai-robotics/semantic-abstraction"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/divide-and-conquer-3d-point-cloud-instance","slug":"divide-and-conquer-3d-point-cloud-instance","title":"Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization","date":"2022-07-22","arxiv_id":"2207.11209","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/divide-and-conquer-3d-point-cloud-instance#ran","syntology_url":"https://syntology.ai/paper/2207.11209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11209"}},"official":{"repos":["weiguangzhao/PBNet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/panoptic-scene-graph-generation","slug":"panoptic-scene-graph-generation","title":"Panoptic Scene Graph Generation","date":"2022-07-22","arxiv_id":"2207.11247","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attacks-on-monocular-pose","slug":"adversarial-attacks-on-monocular-pose","title":"Adversarial Attacks on Monocular Pose Estimation","date":"2022-07-14","arxiv_id":"2207.07032","repositories_listed":1,"syntology":null},{"url":"/paper/egocentric-scene-understanding-via-multimodal-1","slug":"egocentric-scene-understanding-via-multimodal-1","title":"Egocentric Scene Understanding via Multimodal Spatial Rectifier","date":"2022-07-14","arxiv_id":"2207.07077","repositories_listed":1,"syntology":null},{"url":"/paper/distance-matters-in-human-object-interaction","slug":"distance-matters-in-human-object-interaction","title":"Distance Matters in Human-Object Interaction Detection","date":"2022-07-05","arxiv_id":"2207.01869","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-aware-panoptic-segmentation","slug":"uncertainty-aware-panoptic-segmentation","title":"Uncertainty-aware Panoptic Segmentation","date":"2022-06-29","arxiv_id":"2206.14554","repositories_listed":1,"syntology":null},{"url":"/paper/ibiscape-a-simulated-benchmark-for-multi","slug":"ibiscape-a-simulated-benchmark-for-multi","title":"IBISCape: A Simulated Benchmark for multi-modal SLAM Systems Evaluation in Large-scale Dynamic Environments","date":"2022-06-27","arxiv_id":"2206.13455","repositories_listed":1,"syntology":null},{"url":"/paper/fetreg2021-a-challenge-on-placental-vessel","slug":"fetreg2021-a-challenge-on-placental-vessel","title":"Placental Vessel Segmentation and Registration in Fetoscopy: Literature Review and MICCAI FetReg2021 Challenge Findings","date":"2022-06-24","arxiv_id":"2206.12512","repositories_listed":1,"syntology":null},{"url":"/paper/panoramic-panoptic-segmentation-insights-into","slug":"panoramic-panoptic-segmentation-insights-into","title":"Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning","date":"2022-06-21","arxiv_id":"2206.10711","repositories_listed":1,"syntology":null},{"url":"/paper/scim-simultaneous-clustering-inference-and","slug":"scim-simultaneous-clustering-inference-and","title":"SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding","date":"2022-06-21","arxiv_id":"2206.10670","repositories_listed":1,"syntology":null},{"url":"/paper/waymo-open-dataset-panoramic-video-panoptic","slug":"waymo-open-dataset-panoramic-video-panoptic","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","date":"2022-06-15","arxiv_id":"2206.07704","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-foggy-scene-understanding-via","slug":"unsupervised-foggy-scene-understanding-via","title":"Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion","date":"2022-06-10","arxiv_id":"2206.04879","repositories_listed":1,"syntology":null},{"url":"/paper/slot-order-matters-for-compositional-scene","slug":"slot-order-matters-for-compositional-scene","title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","date":"2022-06-03","arxiv_id":"2206.01370","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/slot-order-matters-for-compositional-scene#ran","syntology_url":"https://syntology.ai/paper/2206.01370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01370"}},"official":{"repos":["pemami4911/segregate-relate-imagine"],"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/expressive-scene-graph-generation-using","slug":"expressive-scene-graph-generation-using","title":"Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and Reasoning","date":"2022-05-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/facing-the-void-overcoming-missing-data-in","slug":"facing-the-void-overcoming-missing-data-in","title":"Facing the Void: Overcoming Missing Data in Multi-View Imagery","date":"2022-05-21","arxiv_id":"2205.10592","repositories_listed":1,"syntology":null},{"url":"/paper/spatiality-guided-transformer-for-3d-dense","slug":"spatiality-guided-transformer-for-3d-dense","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","date":"2022-04-22","arxiv_id":"2204.10688","repositories_listed":1,"syntology":null}],"record_sha256":"1cd47cc3f334f9b3d241e31b3aa26307a6ebd89d963b84b8780d729eac522104","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}