{"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/53","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":53,"pages_in_order":107,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/task/object/papers/54","papers":[{"url":null,"slug":"shan-object-level-privacy-detection-via","title":"SHAN: Object-Level Privacy Detection via Inference on Scene Heterogeneous Graph","date":"2024-03-14","arxiv_id":"2403.09172","repositories_listed":0,"syntology":null},{"url":null,"slug":"category-agnostic-pose-estimation-for-point","title":"Category-Agnostic Pose Estimation for Point Clouds","date":"2024-03-12","arxiv_id":"2403.07437","repositories_listed":0,"syntology":null},{"url":null,"slug":"jstr-joint-spatio-temporal-reasoning-for","title":"JSTR: Joint Spatio-Temporal Reasoning for Event-based Moving Object Detection","date":"2024-03-12","arxiv_id":"2403.07436","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-and-search-an-elegant-technique-for","title":"Learn and Search: An Elegant Technique for Object Lookup using Contrastive Learning","date":"2024-03-12","arxiv_id":"2403.07231","repositories_listed":0,"syntology":null},{"url":null,"slug":"taskclip-extend-large-vision-language-model","title":"TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection","date":"2024-03-12","arxiv_id":"2403.08108","repositories_listed":0,"syntology":null},{"url":null,"slug":"tfcounter-polishing-gems-for-training-free","title":"TFCounter:Polishing Gems for Training-Free Object Counting","date":"2024-03-12","arxiv_id":"2405.02301","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-quantification-with-deep","title":"Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation","date":"2024-03-12","arxiv_id":"2403.07741","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-object-throwing-behavior-in","title":"Detection of Object Throwing Behavior in Surveillance Videos","date":"2024-03-11","arxiv_id":"2403.06552","repositories_listed":0,"syntology":null},{"url":null,"slug":"leoclr-leveraging-original-images-for","title":"LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations","date":"2024-03-11","arxiv_id":"2403.06813","repositories_listed":0,"syntology":null},{"url":null,"slug":"clickvos-click-video-object-segmentation","title":"ClickVOS: Click Video Object Segmentation","date":"2024-03-10","arxiv_id":"2403.06130","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-cluster-shifting-for-efficient-and","title":"Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving","date":"2024-03-10","arxiv_id":"2403.06166","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffumatting-synthesizing-arbitrary-objects","title":"DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation","date":"2024-03-10","arxiv_id":"2403.06168","repositories_listed":0,"syntology":null},{"url":null,"slug":"textureless-object-recognition-an-edge-based","title":"Textureless Object Recognition: An Edge-based Approach","date":"2024-03-10","arxiv_id":"2403.06107","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-multitask-learning-for","title":"Transformer based Multitask Learning for Image Captioning and Object Detection","date":"2024-03-10","arxiv_id":"2403.06292","repositories_listed":0,"syntology":null},{"url":null,"slug":"cscnet-class-specified-cascaded-network-for","title":"CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning","date":"2024-03-09","arxiv_id":"2403.05924","repositories_listed":0,"syntology":null},{"url":null,"slug":"do3d-self-supervised-learning-of-decomposed","title":"DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos","date":"2024-03-09","arxiv_id":"2403.05895","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssf-net-spatial-spectral-fusion-network-with","title":"SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Tracking","date":"2024-03-09","arxiv_id":"2403.05852","repositories_listed":0,"syntology":null},{"url":null,"slug":"gsedit-efficient-text-guided-editing-of-3d","title":"GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splatting","date":"2024-03-08","arxiv_id":"2403.05154","repositories_listed":0,"syntology":null},{"url":"/paper/omnicount-multi-label-object-counting-with","slug":"omnicount-multi-label-object-counting-with","title":"OmniCount: Multi-label Object Counting with Semantic-Geometric Priors","date":"2024-03-08","arxiv_id":"2403.05435","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-object-visibility-prediction-in-autonomous","title":"3D Object Visibility Prediction in Autonomous Driving","date":"2024-03-06","arxiv_id":"2403.03681","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-density-guided-temporal-attention","title":"A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video","date":"2024-03-06","arxiv_id":"2403.03461","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-3d-object-centric-representation","title":"Learning 3D object-centric representation through prediction","date":"2024-03-06","arxiv_id":"2403.03730","repositories_listed":0,"syntology":null},{"url":null,"slug":"lodisc-learning-global-local-discriminative","title":"LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition","date":"2024-03-06","arxiv_id":"2403.04066","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-object-tracking-with-camera-lidar","title":"Multi-Object Tracking with Camera-LiDAR Fusion for Autonomous Driving","date":"2024-03-06","arxiv_id":"2403.04112","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-anomaly-detection-based-on-deep","title":"Multimodal Anomaly Detection based on Deep Auto-Encoder for Object Slip Perception of Mobile Manipulation Robots","date":"2024-03-06","arxiv_id":"2403.03563","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-rare-object-detection-in-high","title":"Bootstrapping Rare Object Detection in High-Resolution Satellite Imagery","date":"2024-03-05","arxiv_id":"2403.02736","repositories_listed":0,"syntology":null},{"url":null,"slug":"deconfusetrack-dealing-with-confusion-for","title":"DeconfuseTrack:Dealing with Confusion for Multi-Object Tracking","date":"2024-03-05","arxiv_id":"2403.02767","repositories_listed":0,"syntology":null},{"url":null,"slug":"false-positive-sampling-based-data","title":"False Positive Sampling-based Data Augmentation for Enhanced 3D Object Detection Accuracy","date":"2024-03-05","arxiv_id":"2403.02639","repositories_listed":0,"syntology":null},{"url":null,"slug":"freea-human-object-interaction-detection","title":"FreeA: Human-object Interaction Detection using Free Annotation Labels","date":"2024-03-04","arxiv_id":"2403.01840","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-object-detection-a-study-based-on","title":"Lightweight Object Detection: A Study Based on YOLOv7 Integrated with ShuffleNetv2 and Vision Transformer","date":"2024-03-04","arxiv_id":"2403.01736","repositories_listed":0,"syntology":null},{"url":null,"slug":"riseg-robot-interactive-object-segmentation","title":"RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features","date":"2024-03-04","arxiv_id":"2403.01731","repositories_listed":0,"syntology":null},{"url":null,"slug":"run-time-introspection-of-2d-object-detection","title":"Run-time Introspection of 2D Object Detection in Automated Driving Systems Using Learning Representations","date":"2024-03-02","arxiv_id":"2403.01172","repositories_listed":0,"syntology":null},{"url":null,"slug":"abductive-ego-view-accident-video","title":"Abductive Ego-View Accident Video Understanding for Safe Driving Perception","date":"2024-03-01","arxiv_id":"2403.00436","repositories_listed":0,"syntology":null},{"url":"/paper/dual-pose-invariant-embeddings-learning","slug":"dual-pose-invariant-embeddings-learning","title":"Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval","date":"2024-03-01","arxiv_id":"2403.00272","repositories_listed":0,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 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","sample_list":"/paper/dual-pose-invariant-embeddings-learning#ran","syntology_url":"https://syntology.ai/paper/2403.00272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00272"}},"official":null}},{"url":null,"slug":"learning-causal-features-for-incremental","title":"Learning Causal Features for Incremental Object Detection","date":"2024-03-01","arxiv_id":"2403.00591","repositories_listed":0,"syntology":null},{"url":null,"slug":"lomoe-localized-multi-object-editing-via","title":"LoMOE: Localized Multi-Object Editing via Multi-Diffusion","date":"2024-03-01","arxiv_id":"2403.00437","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-semi-supervised-object-detection-in","title":"Boosting Semi-Supervised Object Detection in Remote Sensing Images With Active Teaching","date":"2024-02-29","arxiv_id":"2402.18958","repositories_listed":0,"syntology":null},{"url":null,"slug":"debiased-novel-category-discovering-and","title":"Debiased Novel Category Discovering and Localization","date":"2024-02-29","arxiv_id":"2402.18821","repositories_listed":0,"syntology":null},{"url":null,"slug":"doze-a-dataset-for-open-vocabulary-zero-shot","title":"DOZE: A Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments","date":"2024-02-29","arxiv_id":"2402.19007","repositories_listed":0,"syntology":null},{"url":null,"slug":"protop-od-explainable-object-detection-with","title":"ProtoP-OD: Explainable Object Detection with Prototypical Parts","date":"2024-02-29","arxiv_id":"2402.19142","repositories_listed":0,"syntology":null},{"url":null,"slug":"semoli-what-moves-together-belongs-together","title":"SeMoLi: What Moves Together Belongs Together","date":"2024-02-29","arxiv_id":"2402.19463","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-driven-dynamic-object-centric-learning","title":"Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization","date":"2024-02-28","arxiv_id":"2402.18447","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-coherence-loss-for-salient-and","title":"Spatial Coherence Loss: All Objects Matter in Salient and Camouflaged Object Detection","date":"2024-02-28","arxiv_id":"2402.18698","repositories_listed":0,"syntology":null},{"url":null,"slug":"unimode-unified-monocular-3d-object-detection","title":"Towards Unified 3D Object Detection via Algorithm and Data Unification","date":"2024-02-28","arxiv_id":"2402.18573","repositories_listed":0,"syntology":null},{"url":null,"slug":"actrack-adding-spatio-temporal-condition-for","title":"ACTrack: Adding Spatio-Temporal Condition for Visual Object Tracking","date":"2024-02-27","arxiv_id":"2403.07914","repositories_listed":0,"syntology":null},{"url":null,"slug":"adl4d-towards-a-contextually-rich-dataset-for","title":"ADL4D: Towards A Contextually Rich Dataset for 4D Activities of Daily Living","date":"2024-02-27","arxiv_id":"2402.17758","repositories_listed":0,"syntology":null},{"url":null,"slug":"deployment-prior-injection-for-run-time","title":"Deployment Prior Injection for Run-time Calibratable Object Detection","date":"2024-02-27","arxiv_id":"2402.17207","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-defense-and-revival-of-bayesian-filtering","title":"In Defense and Revival of Bayesian Filtering for Thermal Infrared Object Tracking","date":"2024-02-27","arxiv_id":"2402.17098","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapm-multi-scale-attention-pyramid-module-for","title":"SaRPFF: A Self-Attention with Register-based Pyramid Feature Fusion module for enhanced RLD detection","date":"2024-02-26","arxiv_id":"2402.16291","repositories_listed":0,"syntology":null},{"url":null,"slug":"outline-guided-object-inpainting-with","title":"Outline-Guided Object Inpainting with Diffusion Models","date":"2024-02-26","arxiv_id":"2402.16421","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallelized-spatiotemporal-binding","title":"Parallelized Spatiotemporal Binding","date":"2024-02-26","arxiv_id":"2402.17077","repositories_listed":0,"syntology":null},{"url":null,"slug":"phygrasp-generalizing-robotic-grasping-with","title":"PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models","date":"2024-02-26","arxiv_id":"2402.16836","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-vehicle-detection-and-urban-traffic","title":"Real-Time Vehicle Detection and Urban Traffic Behavior Analysis Based on UAV Traffic Videos on Mobile Devices","date":"2024-02-26","arxiv_id":"2402.16246","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-language-models-hear-probing-for","title":"What Do Language Models Hear? Probing for Auditory Representations in Language Models","date":"2024-02-26","arxiv_id":"2402.16998","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipose-category-level-object-pose-estimation","title":"CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge","date":"2024-02-24","arxiv_id":"2402.15726","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-is-tracking-point-cloud-multi-sweep","title":"Detection Is Tracking: Point Cloud Multi-Sweep Deep Learning Models Revisited","date":"2024-02-24","arxiv_id":"2402.15756","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-failure-cases-in-multimodal","title":"Exploring Failure Cases in Multimodal Reasoning About Physical Dynamics","date":"2024-02-24","arxiv_id":"2402.15654","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-object-tracking-by-hierarchical-visual","title":"Multi-Object Tracking by Hierarchical Visual Representations","date":"2024-02-24","arxiv_id":"2402.15895","repositories_listed":0,"syntology":null},{"url":null,"slug":"background-denoising-for-ptychography-via","title":"Background Denoising for Ptychography via Wigner Distribution Deconvolution","date":"2024-02-23","arxiv_id":"2402.15353","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-permanence-in-newborn-chicks-is-robust","title":"Object permanence in newborn chicks is robust against opposing evidence","date":"2024-02-22","arxiv_id":"2402.14641","repositories_listed":0,"syntology":null},{"url":null,"slug":"path-planning-based-on-2d-object-bounding-box","title":"Path Planning based on 2D Object Bounding-box","date":"2024-02-22","arxiv_id":"2402.14933","repositories_listed":0,"syntology":null},{"url":null,"slug":"place-anything-into-any-video","title":"Place Anything into Any Video","date":"2024-02-22","arxiv_id":"2402.14316","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo-tla-an-efficient-and-lightweight-small","title":"YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5","date":"2024-02-22","arxiv_id":"2402.14309","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dual-arm-object-rearrangement-for","title":"Learning Dual-arm Object Rearrangement for Cartesian Robots","date":"2024-02-21","arxiv_id":"2402.13634","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-based-object-detection","title":"Unsupervised learning based object detection using Contrastive Learning","date":"2024-02-21","arxiv_id":"2402.13465","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-localisation-of-prostate","title":"Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images","date":"2024-02-21","arxiv_id":"2402.13778","repositories_listed":0,"syntology":null},{"url":null,"slug":"cst-calibration-side-tuning-for-parameter-and","title":"CST: Calibration Side-Tuning for Parameter and Memory Efficient Transfer Learning","date":"2024-02-20","arxiv_id":"2402.12736","repositories_listed":0,"syntology":null},{"url":null,"slug":"dinobot-robot-manipulation-via-retrieval-and","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","date":"2024-02-20","arxiv_id":"2402.13181","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-parameter-mining-and-freezing-for","title":"Efficient Parameter Mining and Freezing for Continual Object Detection","date":"2024-02-20","arxiv_id":"2402.12624","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-towards-domain-generalized-orientated","title":"GOOD: Towards Domain Generalized Orientated Object Detection","date":"2024-02-20","arxiv_id":"2402.12765","repositories_listed":0,"syntology":null},{"url":null,"slug":"olvit-multi-modal-state-tracking-via","title":"OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog","date":"2024-02-20","arxiv_id":"2402.13146","repositories_listed":0,"syntology":null},{"url":null,"slug":"slot-vlm-slowfast-slots-for-video-language","title":"Slot-VLM: SlowFast Slots for Video-Language Modeling","date":"2024-02-20","arxiv_id":"2402.13088","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-object-detection-with-sparse-context","title":"Few-Shot Object Detection with Sparse Context Transformers","date":"2024-02-14","arxiv_id":"2402.09315","repositories_listed":0,"syntology":null},{"url":null,"slug":"moving-object-proposals-with-deep-learned","title":"Moving Object Proposals with Deep Learned Optical Flow for Video Object Segmentation","date":"2024-02-14","arxiv_id":"2402.08882","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-self-supervised-instance","title":"Leveraging Self-Supervised Instance Contrastive Learning for Radar Object Detection","date":"2024-02-13","arxiv_id":"2402.08427","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-discovery-of-object-centric","title":"Unsupervised Discovery of Object-Centric Neural Fields","date":"2024-02-12","arxiv_id":"2402.07376","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-object-level-modeling-for-robust","title":"Semantic Object-level Modeling for Robust Visual Camera Relocalization","date":"2024-02-10","arxiv_id":"2402.06951","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-to-video-conversion-for-overhead-object","title":"Event-to-Video Conversion for Overhead Object Detection","date":"2024-02-09","arxiv_id":"2402.06805","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-2d-3d-dense-correspondences-with","title":"Improving 2D-3D Dense Correspondences with Diffusion Models for 6D Object Pose Estimation","date":"2024-02-09","arxiv_id":"2402.06436","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-with-generative-models-for","title":"Transfer learning with generative models for object detection on limited datasets","date":"2024-02-09","arxiv_id":"2402.06784","repositories_listed":0,"syntology":null},{"url":null,"slug":"binding-dynamics-in-rotating-features","title":"Binding Dynamics in Rotating Features","date":"2024-02-08","arxiv_id":"2402.05627","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-loc-multi-modal-landmark-association-for","title":"CLIP-Loc: Multi-modal Landmark Association for Global Localization in Object-based Maps","date":"2024-02-08","arxiv_id":"2402.06092","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-6d-object-pose-estimators-for","title":"Extending 6D Object Pose Estimators for Stereo Vision","date":"2024-02-08","arxiv_id":"2402.05610","repositories_listed":0,"syntology":null},{"url":null,"slug":"funcgrasp-learning-object-centric-neural","title":"FuncGrasp: Learning Object-Centric Neural Grasp Functions from Single Annotated Example Object","date":"2024-02-08","arxiv_id":"2402.05644","repositories_listed":0,"syntology":null},{"url":null,"slug":"instagen-enhancing-object-detection-by","title":"InstaGen: Enhancing Object Detection by Training on Synthetic Dataset","date":"2024-02-08","arxiv_id":"2402.05937","repositories_listed":0,"syntology":null},{"url":null,"slug":"ncrf-neural-contact-radiance-fields-for-free","title":"NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interaction","date":"2024-02-08","arxiv_id":"2402.05532","repositories_listed":0,"syntology":null},{"url":null,"slug":"point-vos-pointing-up-video-object","title":"Point-VOS: Pointing Up Video Object Segmentation","date":"2024-02-08","arxiv_id":"2402.05917","repositories_listed":0,"syntology":null},{"url":null,"slug":"color-recognition-in-challenging-lighting","title":"Color Recognition in Challenging Lighting Environments: CNN Approach","date":"2024-02-07","arxiv_id":"2402.04762","repositories_listed":0,"syntology":null},{"url":null,"slug":"tactile-based-object-retrieval-from-granular","title":"Tactile-based Object Retrieval From Granular Media","date":"2024-02-07","arxiv_id":"2402.04536","repositories_listed":0,"syntology":null},{"url":null,"slug":"text2street-controllable-text-to-image","title":"Text2Street: Controllable Text-to-image Generation for Street Views","date":"2024-02-07","arxiv_id":"2402.04504","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-accurate-camera-based-3d-object","title":"Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration","date":"2024-02-07","arxiv_id":"2402.04883","repositories_listed":0,"syntology":null},{"url":null,"slug":"dexdiffuser-generating-dexterous-grasps-with","title":"DexDiffuser: Generating Dexterous Grasps with Diffusion Models","date":"2024-02-05","arxiv_id":"2402.02989","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-a-video-customized-video-generation","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","date":"2024-02-05","arxiv_id":"2402.03162","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-universe-indoor-scene-generation-using","title":"Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases","date":"2024-02-05","arxiv_id":"2403.09675","repositories_listed":0,"syntology":null},{"url":null,"slug":"cofinet-unveiling-camouflaged-objects-with","title":"CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse","date":"2024-02-03","arxiv_id":"2402.02217","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-slot-interpreters-grounding-object","title":"Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations","date":"2024-02-02","arxiv_id":"2403.07887","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-objects-in-a-cluttered-world","title":"Seeing Objects in a Cluttered World: Computational Objectness from Motion in Video","date":"2024-02-02","arxiv_id":"2402.01126","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-world-modeling-via-semantic-vector","title":"Neural Language of Thought Models","date":"2024-02-02","arxiv_id":"2402.01203","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsjnet-a-multi-modality-target-and-semantic","title":"TSJNet: A Multi-modality Target and Semantic Awareness Joint-driven Image Fusion Network","date":"2024-02-02","arxiv_id":"2402.01212","repositories_listed":0,"syntology":null},{"url":null,"slug":"finebio-a-fine-grained-video-dataset-of","title":"FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation","date":"2024-02-01","arxiv_id":"2402.00293","repositories_listed":0,"syntology":null}],"record_sha256":"d12a266d8ad2a42cb7c6c53ae0cee851e5a8d2a83960828fc8607e75051d5610","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}