{"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/44","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":44,"pages_in_order":107,"rows_per_page":100,"rows":[4301,4400],"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/43","next":"/task/object/papers/45","papers":[{"url":null,"slug":"joint-reconstruction-of-spatially-coherent","title":"Joint Reconstruction of Spatially-Coherent and Realistic Clothed Humans and Objects from a Single Image","date":"2025-02-25","arxiv_id":"2502.18150","repositories_listed":0,"syntology":null},{"url":null,"slug":"crtrack-low-light-semi-supervised-multi","title":"CRTrack: Low-Light Semi-Supervised Multi-object Tracking Based on Consistency Regularization","date":"2025-02-24","arxiv_id":"2502.16809","repositories_listed":0,"syntology":null},{"url":"/paper/sparc-score-prompting-and-adaptive-fusion-for","slug":"sparc-score-prompting-and-adaptive-fusion-for","title":"SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models","date":"2025-02-24","arxiv_id":"2502.16911","repositories_listed":0,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":12,"phrase":"6 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; 6 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/sparc-score-prompting-and-adaptive-fusion-for#ran","syntology_url":"https://syntology.ai/paper/2502.16911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16911"}},"official":null}},{"url":null,"slug":"v-hop-visuo-haptic-6d-object-pose-tracking","title":"V-HOP: Visuo-Haptic 6D Object Pose Tracking","date":"2025-02-24","arxiv_id":"2502.17434","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometry-aware-3d-salient-object-detection","title":"Geometry-Aware 3D Salient Object Detection Network","date":"2025-02-23","arxiv_id":"2502.16488","repositories_listed":0,"syntology":null},{"url":null,"slug":"mqadet-a-plug-and-play-paradigm-for-enhancing","title":"MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering","date":"2025-02-23","arxiv_id":"2502.16486","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-about-affordances-causal-and","title":"Reasoning about Affordances: Causal and Compositional Reasoning in LLMs","date":"2025-02-23","arxiv_id":"2502.16606","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-background-information-in","title":"The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting","date":"2025-02-21","arxiv_id":"2502.15389","repositories_listed":0,"syntology":null},{"url":null,"slug":"odverse33-is-the-new-yolo-version-always","title":"ODVerse33: Is the New YOLO Version Always Better? A Multi Domain benchmark from YOLO v5 to v11","date":"2025-02-20","arxiv_id":"2502.14314","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-less-feel-more-sim-to-real-rl-for","title":"Watch Less, Feel More: Sim-to-Real RL for Generalizable Articulated Object Manipulation via Motion Adaptation and Impedance Control","date":"2025-02-20","arxiv_id":"2502.14457","repositories_listed":0,"syntology":null},{"url":null,"slug":"capturing-rich-behavior-representations-a","title":"Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning","date":"2025-02-19","arxiv_id":"2502.13754","repositories_listed":0,"syntology":null},{"url":null,"slug":"mex-memory-efficient-approach-to-referring","title":"MEX: Memory-efficient Approach to Referring Multi-Object Tracking","date":"2025-02-19","arxiv_id":"2502.13875","repositories_listed":0,"syntology":null},{"url":null,"slug":"msvcod-a-large-scale-multi-scene-dataset-for","title":"MSVCOD:A Large-Scale Multi-Scene Dataset for Video Camouflage Object Detection","date":"2025-02-19","arxiv_id":"2502.13859","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-binding-in-contrastive","title":"Object-centric Binding in Contrastive Language-Image Pretraining","date":"2025-02-19","arxiv_id":"2502.14113","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-pose-estimation-with-neural-population","title":"Object-Pose Estimation With Neural Population Codes","date":"2025-02-19","arxiv_id":"2502.13403","repositories_listed":0,"syntology":null},{"url":null,"slug":"raptor-refined-approach-for-product-table","title":"RAPTOR: Refined Approach for Product Table Object Recognition","date":"2025-02-19","arxiv_id":"2502.14918","repositories_listed":0,"syntology":null},{"url":null,"slug":"cast-component-aligned-3d-scene","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","date":"2025-02-18","arxiv_id":"2502.12894","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-level-moving-object-segmentation","title":"Instance-Level Moving Object Segmentation from a Single Image with Events","date":"2025-02-18","arxiv_id":"2502.12975","repositories_listed":0,"syntology":null},{"url":null,"slug":"rhino-learning-real-time-humanoid-human","title":"RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations","date":"2025-02-18","arxiv_id":"2502.13134","repositories_listed":0,"syntology":null},{"url":null,"slug":"roburcdet-enhancing-robustness-of-radar","title":"RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection","date":"2025-02-18","arxiv_id":"2502.13071","repositories_listed":0,"syntology":null},{"url":null,"slug":"roi-nerfs-hi-fi-visualization-of-objects-of","title":"ROI-NeRFs: Hi-Fi Visualization of Objects of Interest within a Scene by NeRFs Composition","date":"2025-02-18","arxiv_id":"2502.12673","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-monocular-event-camera-motion-capture","title":"A Monocular Event-Camera Motion Capture System","date":"2025-02-17","arxiv_id":"2502.12113","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-transparent-object-pose-estimation","title":"Enhancing Transparent Object Pose Estimation: A Fusion of GDR-Net and Edge Detection","date":"2025-02-17","arxiv_id":"2502.12027","repositories_listed":0,"syntology":null},{"url":null,"slug":"revealing-bias-formation-in-deep-neural","title":"Revealing Bias Formation in Deep Neural Networks Through the Geometric Mechanisms of Human Visual Decoupling","date":"2025-02-17","arxiv_id":"2502.11809","repositories_listed":0,"syntology":null},{"url":null,"slug":"focalcount-towards-class-count-imbalance-in","title":"FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting","date":"2025-02-15","arxiv_id":"2502.10677","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-meta-and-object-level","title":"Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering","date":"2025-02-14","arxiv_id":"2502.10338","repositories_listed":0,"syntology":null},{"url":null,"slug":"hippo-harnessing-image-to-3d-priors-for-model","title":"HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimation","date":"2025-02-14","arxiv_id":"2502.10606","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-latent-action-learning","title":"Object-Centric Latent Action Learning","date":"2025-02-13","arxiv_id":"2502.09680","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multi-agent-satellite-servicing-with","title":"Safe Multi-agent Satellite Servicing with Control Barrier Functions","date":"2025-02-13","arxiv_id":"2502.10480","repositories_listed":0,"syntology":null},{"url":null,"slug":"cinemaster-a-3d-aware-and-controllable","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","date":"2025-02-12","arxiv_id":"2502.08639","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulate-that-object-part-atop-3d-part","title":"Articulate That Object Part (ATOP): 3D Part Articulation from Text and Motion Personalization","date":"2025-02-11","arxiv_id":"2502.07278","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-object-detection-based-on-de","title":"Dense Object Detection Based on De-homogenized Queries","date":"2025-02-11","arxiv_id":"2502.07194","repositories_listed":0,"syntology":null},{"url":null,"slug":"vidcraft3-camera-object-and-lighting-control","title":"VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation","date":"2025-02-11","arxiv_id":"2502.07531","repositories_listed":0,"syntology":null},{"url":null,"slug":"secure-visual-data-processing-via-federated","title":"Secure Visual Data Processing via Federated Learning","date":"2025-02-09","arxiv_id":"2502.06889","repositories_listed":0,"syntology":null},{"url":null,"slug":"lp-detr-layer-wise-progressive-relations-for","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","date":"2025-02-07","arxiv_id":"2502.05147","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-clustering-for-prefractured-mesh","title":"Neural Clustering for Prefractured Mesh Generation in Real-time Object Destruction","date":"2025-02-07","arxiv_id":"2502.04615","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-object-detection-and-pose-estimation","title":"Advanced Object Detection and Pose Estimation with Hybrid Task Cascade and High-Resolution Networks","date":"2025-02-06","arxiv_id":"2502.03877","repositories_listed":0,"syntology":null},{"url":null,"slug":"anyplace-learning-generalized-object","title":"AnyPlace: Learning Generalized Object Placement for Robot Manipulation","date":"2025-02-06","arxiv_id":"2502.04531","repositories_listed":0,"syntology":null},{"url":"/paper/enhancing-people-localisation-in-drone","slug":"enhancing-people-localisation-in-drone","title":"Enhancing people localisation in drone imagery for better crowd management by utilising every pixel in high-resolution images","date":"2025-02-06","arxiv_id":"2502.04014","repositories_listed":0,"syntology":null},{"url":null,"slug":"hd-epic-a-highly-detailed-egocentric-video","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","date":"2025-02-06","arxiv_id":"2502.04144","repositories_listed":0,"syntology":null},{"url":null,"slug":"partedit-fine-grained-image-editing-using-pre","title":"PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models","date":"2025-02-06","arxiv_id":"2502.04050","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-a-vision-language-action-model-for","title":"Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture","date":"2025-02-06","arxiv_id":"2502.04558","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-cognitive-semantic-communications-enabled","title":"UAV Cognitive Semantic Communications Enabled by Knowledge Graph for Robust Object Detection","date":"2025-02-06","arxiv_id":"2502.03761","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-clip-features-for-enhanced","title":"Disentangling CLIP for Multi-Object Perception","date":"2025-02-05","arxiv_id":"2502.02977","repositories_listed":0,"syntology":null},{"url":null,"slug":"zisvfm-zero-shot-object-instance-segmentation","title":"ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models","date":"2025-02-05","arxiv_id":"2502.03266","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulate-anymesh-open-vocabulary-3d","title":"Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modeling","date":"2025-02-04","arxiv_id":"2502.02590","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-you-move-these-over-there-an-llm-based-vr","title":"Can You Move These Over There? An LLM-based VR Mover for Supporting Object Manipulation","date":"2025-02-04","arxiv_id":"2502.02201","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-object-hallucinations-in-large-1","title":"Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration","date":"2025-02-04","arxiv_id":"2502.01969","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-quantification-for-collaborative","title":"Uncertainty Quantification for Collaborative Object Detection Under Adversarial Attacks","date":"2025-02-04","arxiv_id":"2502.02537","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-object-goal-pushing-with-mobile","title":"Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning","date":"2025-02-03","arxiv_id":"2502.01546","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-in-large-vision-5","title":"Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding","date":"2025-02-03","arxiv_id":"2502.01056","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-cellular-automata-for-decentralized","title":"Neural Cellular Automata for Decentralized Sensing using a Soft Inductive Sensor Array for Distributed Manipulator Systems","date":"2025-02-03","arxiv_id":"2502.01242","repositories_listed":0,"syntology":null},{"url":null,"slug":"realrag-retrieval-augmented-realistic-image","title":"RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning","date":"2025-02-02","arxiv_id":"2502.00848","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-human-sketches-help-empowering","title":"Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches","date":"2025-01-31","arxiv_id":"2501.19329","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-object-detection-for-indoor","title":"Adaptive Object Detection for Indoor Navigation Assistance: A Performance Evaluation of Real-Time Algorithms","date":"2025-01-30","arxiv_id":"2501.18444","repositories_listed":0,"syntology":null},{"url":null,"slug":"run-reversible-unfolding-network-for","title":"RUN: Reversible Unfolding Network for Concealed Object Segmentation","date":"2025-01-30","arxiv_id":"2501.18783","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-interactive-3d-multi-object-removal","title":"Efficient Interactive 3D Multi-Object Removal","date":"2025-01-29","arxiv_id":"2501.17636","repositories_listed":0,"syntology":null},{"url":null,"slug":"dinostar-deep-iterative-neural-object","title":"DINOSTAR: Deep Iterative Neural Object Detector Self-Supervised Training for Roadside LiDAR Applications","date":"2025-01-28","arxiv_id":"2501.17076","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-reconstruction-of-non-visible-surfaces-of","title":"3D Reconstruction of non-visible surfaces of objects from a Single Depth View -- Comparative Study","date":"2025-01-27","arxiv_id":"2501.16101","repositories_listed":0,"syntology":null},{"url":null,"slug":"objects-matter-object-centric-world-models","title":"Objects matter: object-centric world models improve reinforcement learning in visually complex environments","date":"2025-01-27","arxiv_id":"2501.16443","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-from-generated-multi","title":"Domain Adaptation from Generated Multi-Weather Images for Unsupervised Maritime Object Classification","date":"2025-01-26","arxiv_id":"2501.15503","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-hallucination-in-large-vision","title":"Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities","date":"2025-01-25","arxiv_id":"2501.15046","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimation-theoretic-analysis-of-lensless","title":"Estimation-theoretic analysis of lensless imaging","date":"2025-01-24","arxiv_id":"2501.14727","repositories_listed":0,"syntology":null},{"url":"/paper/referdino-referring-video-object-segmentation","slug":"referdino-referring-video-object-segmentation","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","date":"2025-01-24","arxiv_id":"2501.14607","repositories_listed":0,"syntology":null},{"url":null,"slug":"csaot-cooperative-multi-agent-system-for","title":"CSAOT: Cooperative Multi-Agent System for Active Object Tracking","date":"2025-01-23","arxiv_id":"2501.13994","repositories_listed":0,"syntology":null},{"url":null,"slug":"curiousbot-interactive-mobile-exploration-via","title":"CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph","date":"2025-01-23","arxiv_id":"2501.13338","repositories_listed":0,"syntology":null},{"url":null,"slug":"mona-moving-object-detection-from-videos-shot","title":"MONA: Moving Object Detection from Videos Shot by Dynamic Camera","date":"2025-01-22","arxiv_id":"2501.13183","repositories_listed":0,"syntology":null},{"url":null,"slug":"slot-bert-self-supervised-object-discovery-in","title":"Slot-BERT: Self-supervised Object Discovery in Surgical Video","date":"2025-01-21","arxiv_id":"2501.12477","repositories_listed":0,"syntology":null},{"url":null,"slug":"toffe-temporally-binned-object-flow-from","title":"TOFFE -- Temporally-binned Object Flow from Events for High-speed and Energy-Efficient Object Detection and Tracking","date":"2025-01-21","arxiv_id":"2501.12482","repositories_listed":0,"syntology":null},{"url":null,"slug":"green-video-camouflaged-object-detection","title":"Green Video Camouflaged Object Detection","date":"2025-01-19","arxiv_id":"2501.10914","repositories_listed":0,"syntology":null},{"url":null,"slug":"flora-formal-language-model-enables-robust","title":"FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis","date":"2025-01-17","arxiv_id":"2501.09887","repositories_listed":0,"syntology":null},{"url":null,"slug":"monosowa-scalable-monocular-3d-object","title":"MonoSOWA: Scalable monocular 3D Object detector Without human Annotations","date":"2025-01-16","arxiv_id":"2501.09481","repositories_listed":0,"syntology":null},{"url":null,"slug":"re-pose-synergizing-reinforcement-learning","title":"RE-POSE: Synergizing Reinforcement Learning-Based Partitioning and Offloading for Edge Object Detection","date":"2025-01-16","arxiv_id":"2501.09465","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-corner-cases-high-resolution","title":"Bootstrapping Corner Cases: High-Resolution Inpainting for Safety Critical Detect and Avoid for Automated Flying","date":"2025-01-14","arxiv_id":"2501.08142","repositories_listed":0,"syntology":null},{"url":null,"slug":"david-modeling-dynamic-affordance-of-3d","title":"DAViD: Modeling Dynamic Affordance of 3D Objects using Pre-trained Video Diffusion Models","date":"2025-01-14","arxiv_id":"2501.08333","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-contextual-anomalies-by-discovering","title":"Detecting Contextual Anomalies by Discovering Consistent Spatial Regions","date":"2025-01-14","arxiv_id":"2501.08470","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-2d-gaussian-splatting","title":"Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models","date":"2025-01-14","arxiv_id":"2501.08174","repositories_listed":0,"syntology":null},{"url":null,"slug":"smarteraser-remove-anything-from-images-using","title":"SmartEraser: Remove Anything from Images using Masked-Region Guidance","date":"2025-01-14","arxiv_id":"2501.08279","repositories_listed":0,"syntology":null},{"url":null,"slug":"blobgen-vid-compositional-text-to-video","title":"BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations","date":"2025-01-13","arxiv_id":"2501.07647","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-learning-for-3d-hand-object","title":"Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics","date":"2025-01-13","arxiv_id":"2501.07100","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-sam-label-efficient-part-segmentation","title":"Guided SAM: Label-Efficient Part Segmentation","date":"2025-01-13","arxiv_id":"2501.07434","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocord-open-campus-object-removal-dataset","title":"VDOR: A Video-based Dataset for Object Removal via Sequence Consistency","date":"2025-01-13","arxiv_id":"2501.07397","repositories_listed":0,"syntology":null},{"url":null,"slug":"vageo-view-specific-attention-for-cross-view","title":"VAGeo: View-specific Attention for Cross-View Object Geo-Localization","date":"2025-01-13","arxiv_id":"2501.07194","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamba-moc-a-multicategory-remote-object","title":"Mamba-MOC: A Multicategory Remote Object Counting via State Space Model","date":"2025-01-12","arxiv_id":"2501.06697","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniq-unified-decoder-with-task-specific","title":"UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation","date":"2025-01-10","arxiv_id":"2501.05687","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-simple-to-complex-skills-the-case-of-in","title":"From Simple to Complex Skills: The Case of In-Hand Object Reorientation","date":"2025-01-09","arxiv_id":"2501.05439","repositories_listed":0,"syntology":null},{"url":null,"slug":"perception-as-control-fine-grained","title":"Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation","date":"2025-01-09","arxiv_id":"2501.05020","repositories_listed":0,"syntology":null},{"url":null,"slug":"upaq-a-framework-for-real-time-and-energy","title":"UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles","date":"2025-01-08","arxiv_id":"2501.04213","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxdepthnet-real-time-monocular-3d-object","title":"AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features","date":"2025-01-07","arxiv_id":"2501.03700","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-transfer-human-hand-skills-for","title":"Learning to Transfer Human Hand Skills for Robot Manipulations","date":"2025-01-07","arxiv_id":"2501.04169","repositories_listed":0,"syntology":null},{"url":null,"slug":"hogsa-bimanual-hand-object-interaction","title":"HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation","date":"2025-01-06","arxiv_id":"2501.02845","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-gaze-boosts-object-centered","title":"Human Gaze Boosts Object-Centered Representation Learning","date":"2025-01-06","arxiv_id":"2501.02966","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobi-multimodal-object-inpainting-using","title":"MObI: Multimodal Object Inpainting Using Diffusion Models","date":"2025-01-06","arxiv_id":"2501.03173","repositories_listed":0,"syntology":null},{"url":null,"slug":"through-the-mask-mask-based-motion","title":"Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation","date":"2025-01-06","arxiv_id":"2501.03059","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-sequential-pretraining-for","title":"Autoregressive Sequential Pretraining for Visual Tracking","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"be-more-specific-evaluating-object-centric","title":"Be More Specific: Evaluating Object-centric Realism in Synthetic Images","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bigs-bimanual-category-agnostic-interaction","title":"BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"camouflage-anything-learning-to-hide-using","title":"Camouflage Anything: Learning to Hide using Controlled Out-painting and Representation Engineering","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"camuvid-calibration-free-multi-view-detection","title":"CaMuViD: Calibration-Free Multi-View Detection","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"composing-parts-for-expressive-object","title":"Composing Parts for Expressive Object Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"2f4b9c18b1903eae9247bff18d67c2dad3195ca3b5bc489b6d6f4da278922853","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}