{"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/46","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":46,"pages_in_order":107,"rows_per_page":100,"rows":[4501,4600],"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/45","next":"/task/object/papers/47","papers":[{"url":null,"slug":"identifying-reliable-predictions-in-detection","title":"Identifying Reliable Predictions in Detection Transformers","date":"2024-12-02","arxiv_id":"2412.01782","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-agnostic-3d-lifting-in-space-and-time","title":"Object Agnostic 3D Lifting in Space and Time","date":"2024-12-02","arxiv_id":"2412.01166","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-tracking-in-a-360-o-view-a-novel","title":"Object Tracking in a $360^o$ View: A Novel Perspective on Bridging the Gap to Biomedical Advancements","date":"2024-12-02","arxiv_id":"2412.01119","repositories_listed":0,"syntology":null},{"url":"/paper/bev-sushi-multi-target-multi-camera-3d","slug":"bev-sushi-multi-target-multi-camera-3d","title":"MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos","date":"2024-12-01","arxiv_id":"2412.00692","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-object-detectors-via-collective","title":"Explaining Object Detectors via Collective Contribution of Pixels","date":"2024-12-01","arxiv_id":"2412.00666","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-lidar-editing-with-controllable","title":"LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes","date":"2024-11-30","arxiv_id":"2412.00592","repositories_listed":0,"syntology":null},{"url":null,"slug":"motion-modes-what-could-happen-next","title":"Motion Modes: What Could Happen Next?","date":"2024-11-29","arxiv_id":"2412.00148","repositories_listed":0,"syntology":null},{"url":null,"slug":"quota-quantifying-objects-with-text-to-image","title":"QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain","date":"2024-11-29","arxiv_id":"2411.19534","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-to-sim-via-end-to-end-differentiable","title":"One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Rendering","date":"2024-11-29","arxiv_id":"2412.00259","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-bayesian-scene-reconstruction-by","title":"Robust Bayesian Scene Reconstruction by Leveraging Retrieval-Augmented Priors","date":"2024-11-29","arxiv_id":"2411.19461","repositories_listed":0,"syntology":null},{"url":null,"slug":"objectrelator-enabling-cross-view-object","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding in Ego-Centric and Exo-Centric Videos","date":"2024-11-28","arxiv_id":"2411.19083","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-neural-processes-for","title":"Semi-Supervised Neural Processes for Articulated Object Interactions","date":"2024-11-28","arxiv_id":"2412.00145","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-object-language-modeling-solm","title":"Structured Object Language Modeling (SoLM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising","date":"2024-11-28","arxiv_id":"2411.19301","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-extended-object-tracking-with","title":"A comparison of extended object tracking with multi-modal sensors in indoor environment","date":"2024-11-27","arxiv_id":"2411.18476","repositories_listed":0,"syntology":null},{"url":null,"slug":"opcap-object-aware-prompting-captioning","title":"OPCap:Object-aware Prompting Captioning","date":"2024-11-27","arxiv_id":"2412.00095","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-multispectral-object-detection-a","title":"Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks","date":"2024-11-27","arxiv_id":"2411.18288","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-hoi-vision-language-models-for","title":"VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis","date":"2024-11-27","arxiv_id":"2411.18038","repositories_listed":0,"syntology":null},{"url":null,"slug":"anchorcrafter-animate-cyberanchors-saling","title":"AnchorCrafter: Animate CyberAnchors Saling Your Products via Human-Object Interacting Video Generation","date":"2024-11-26","arxiv_id":"2411.17383","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-spectral-graph-for-object-context","title":"Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation","date":"2024-11-26","arxiv_id":"2411.17150","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-aleatoric-uncertainty-in-object","title":"Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models","date":"2024-11-26","arxiv_id":"2411.17767","repositories_listed":0,"syntology":null},{"url":null,"slug":"gmflow-global-motion-guided-recurrent-flow","title":"GMFlow: Global Motion-Guided Recurrent Flow for 6D Object Pose Estimation","date":"2024-11-26","arxiv_id":"2411.17174","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-road-object-importance-estimation-a-new","title":"On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance","date":"2024-11-26","arxiv_id":"2411.17152","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-3d-object-generation-through-pbr","title":"Boosting 3D Object Generation through PBR Materials","date":"2024-11-25","arxiv_id":"2411.16080","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-features-for-zero-shot-6dof-object","title":"Diffusion Features for Zero-Shot 6DoF Object Pose Estimation","date":"2024-11-25","arxiv_id":"2411.16668","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperspectral-image-cross-domain-object","title":"Hyperspectral Image Cross-Domain Object Detection Method based on Spectral-Spatial Feature Alignment","date":"2024-11-25","arxiv_id":"2411.16772","repositories_listed":0,"syntology":null},{"url":null,"slug":"leverage-task-context-for-object-affordance","title":"Leverage Task Context for Object Affordance Ranking","date":"2024-11-25","arxiv_id":"2411.16082","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-foundation-models-to-learn-the","title":"Leveraging Foundation Models To learn the shape of semi-fluid deformable objects","date":"2024-11-25","arxiv_id":"2411.16802","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-episodic-memory-visual-query","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","date":"2024-11-25","arxiv_id":"2411.16934","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-octree-graph-for-3d-scene","title":"Open-Vocabulary Octree-Graph for 3D Scene Understanding","date":"2024-11-25","arxiv_id":"2411.16253","repositories_listed":0,"syntology":null},{"url":null,"slug":"unopose-unseen-object-pose-estimation-with-an","title":"UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image","date":"2024-11-25","arxiv_id":"2411.16106","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoorion-tokenizing-object-dynamics-in","title":"VideoOrion: Tokenizing Object Dynamics in Videos","date":"2024-11-25","arxiv_id":"2411.16156","repositories_listed":0,"syntology":null},{"url":null,"slug":"fasttracktr-towards-fast-multi-object","title":"FastTrackTr:Towards Fast Multi-Object Tracking with Transformers","date":"2024-11-24","arxiv_id":"2411.15811","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-open-vocabulary-object","title":"Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation","date":"2024-11-23","arxiv_id":"2411.15620","repositories_listed":0,"syntology":null},{"url":null,"slug":"twin-trigger-generative-networks-for-backdoor","title":"Twin Trigger Generative Networks for Backdoor Attacks against Object Detection","date":"2024-11-23","arxiv_id":"2411.15439","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-real-time-detr-approach-to-bangladesh-road","title":"A Real-Time DETR Approach to Bangladesh Road Object Detection for Autonomous Vehicles","date":"2024-11-22","arxiv_id":"2411.15110","repositories_listed":0,"syntology":null},{"url":null,"slug":"ict-image-object-cross-level-trusted","title":"ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models","date":"2024-11-22","arxiv_id":"2411.15268","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-aware-generalized-referring","title":"Instance-Aware Generalized Referring Expression Segmentation","date":"2024-11-22","arxiv_id":"2411.15087","repositories_listed":0,"syntology":null},{"url":null,"slug":"baking-gaussian-splatting-into-diffusion","title":"Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction","date":"2024-11-21","arxiv_id":"2411.14384","repositories_listed":0,"syntology":null},{"url":null,"slug":"sempose-a-single-end-to-end-network-for-multi","title":"SEMPose: A Single End-to-end Network for Multi-object Pose Estimation","date":"2024-11-21","arxiv_id":"2411.14002","repositories_listed":0,"syntology":null},{"url":null,"slug":"click-single-object-tracking-video-object","title":"ClickTrack: Towards Real-time Interactive Single Object Tracking","date":"2024-11-20","arxiv_id":"2411.13183","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-guided-zero-shot-object-localization","title":"Text-guided Zero-Shot Object Localization","date":"2024-11-18","arxiv_id":"2411.11357","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-compositional-scenes-via-text-to","title":"Generating Compositional Scenes via Text-to-image RGBA Instance Generation","date":"2024-11-16","arxiv_id":"2411.10913","repositories_listed":0,"syntology":null},{"url":null,"slug":"radio-frequency-ray-tracing-with-neural","title":"Radio Frequency Ray Tracing with Neural Object Representation","date":"2024-11-16","arxiv_id":"2411.18635","repositories_listed":0,"syntology":null},{"url":null,"slug":"coloredit-training-free-image-guided-color","title":"ColorEdit: Training-free Image-Guided Color editing with diffusion model","date":"2024-11-15","arxiv_id":"2411.10232","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-ai-driven-people-tracking-and","title":"Real-Time AI-Driven People Tracking and Counting Using Overhead Cameras","date":"2024-11-15","arxiv_id":"2411.10072","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-tensor-representation-for-robust","title":"Structure Tensor Representation for Robust Oriented Object Detection","date":"2024-11-15","arxiv_id":"2411.10497","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-linguistic-agent-towards-collaborative","title":"Visual-Linguistic Agent: Towards Collaborative Contextual Object Reasoning","date":"2024-11-15","arxiv_id":"2411.10252","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-reconstruction-of-hand-object","title":"Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation","date":"2024-11-14","arxiv_id":"2411.09572","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-processing-for-motion-magnification","title":"Image Processing for Motion Magnification","date":"2024-11-14","arxiv_id":"2411.09555","repositories_listed":0,"syntology":null},{"url":null,"slug":"leap-d-a-novel-prompt-based-approach-for","title":"LEAP:D - A Novel Prompt-based Approach for Domain-Generalized Aerial Object Detection","date":"2024-11-14","arxiv_id":"2411.09180","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-tailed-object-detection-pre-training","title":"Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction","date":"2024-11-14","arxiv_id":"2411.09453","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-multi-object-tracking-with-semi-supervised","title":"3D Multi-Object Tracking with Semi-Supervised GRU-Kalman Filter","date":"2024-11-13","arxiv_id":"2411.08433","repositories_listed":0,"syntology":null},{"url":null,"slug":"methodology-for-a-statistical-analysis-of","title":"Methodology for a Statistical Analysis of Influencing Factors on 3D Object Detection Performance","date":"2024-11-13","arxiv_id":"2411.08482","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-object-detection-using-depth-and","title":"Multimodal Object Detection using Depth and Image Data for Manufacturing Parts","date":"2024-11-13","arxiv_id":"2411.09062","repositories_listed":0,"syntology":null},{"url":null,"slug":"nl-slam-for-oc-vln-natural-language-grounded","title":"Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation","date":"2024-11-12","arxiv_id":"2411.07848","repositories_listed":0,"syntology":null},{"url":null,"slug":"edify-3d-scalable-high-quality-3d-asset","title":"Edify 3D: Scalable High-Quality 3D Asset Generation","date":"2024-11-11","arxiv_id":"2411.07135","repositories_listed":0,"syntology":null},{"url":null,"slug":"hstrack-bootstrap-end-to-end-multi-camera-3d","title":"SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking","date":"2024-11-11","arxiv_id":"2411.06780","repositories_listed":0,"syntology":null},{"url":null,"slug":"track-any-peppers-weakly-supervised-sweet","title":"Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMs","date":"2024-11-11","arxiv_id":"2411.06702","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-collision-risk-estimation-via","title":"FuzzRisk: Online Collision Risk Estimation for Autonomous Vehicles based on Depth-Aware Object Detection via Fuzzy Inference","date":"2024-11-09","arxiv_id":"2411.08060","repositories_listed":0,"syntology":null},{"url":null,"slug":"vitoc-vision-transformer-and-object-aware","title":"ViTOC: Vision Transformer and Object-aware Captioner","date":"2024-11-09","arxiv_id":"2411.07265","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-object-detection-towards-unified","title":"Open-set object detection: towards unified problem formulation and benchmarking","date":"2024-11-08","arxiv_id":"2411.05564","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplebev-improved-lidar-camera-fusion","title":"SimpleBEV: Improved LiDAR-Camera Fusion Architecture for 3D Object Detection","date":"2024-11-08","arxiv_id":"2411.05292","repositories_listed":0,"syntology":null},{"url":null,"slug":"h-pope-hierarchical-polling-based-probing","title":"H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in Large Vision-Language Models","date":"2024-11-06","arxiv_id":"2411.04077","repositories_listed":0,"syntology":null},{"url":null,"slug":"erup-yolo-enhancing-object-detection","title":"ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing","date":"2024-11-05","arxiv_id":"2411.02799","repositories_listed":0,"syntology":null},{"url":null,"slug":"out-of-distribution-recovery-with-object","title":"Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning","date":"2024-11-05","arxiv_id":"2411.03294","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-cross-modality-learning-for","title":"Self-supervised cross-modality learning for uncertainty-aware object detection and recognition in applications which lack pre-labelled training data","date":"2024-11-05","arxiv_id":"2411.03082","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-gaze-behavior-boosts-self-supervised","title":"Active Gaze Behavior Boosts Self-Supervised Object Learning","date":"2024-11-04","arxiv_id":"2411.01969","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-top-down-information-for-self","title":"Bootstrapping Top-down Information for Self-modulating Slot Attention","date":"2024-11-04","arxiv_id":"2411.01801","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect-an-object-at-once-without-fine-tuning","title":"Detect an Object At Once without Fine-tuning","date":"2024-11-04","arxiv_id":"2411.02181","repositories_listed":0,"syntology":null},{"url":"/paper/sira-scalable-inter-frame-relation-and-1","slug":"sira-scalable-inter-frame-relation-and-1","title":"SIRA: Scalable Inter-frame Relation and Association for Radar Perception","date":"2024-11-04","arxiv_id":"2411.02220","repositories_listed":0,"syntology":null},{"url":null,"slug":"aquafuse-waterbody-fusion-for-physics-guided","title":"AquaFuse: Waterbody Fusion for Physics Guided View Synthesis of Underwater Scenes","date":"2024-11-02","arxiv_id":"2411.01119","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-tracing-for-cascading-changes-of","title":"Distributed Tracing for Cascading Changes of Objects in the Kubernetes Control Plane","date":"2024-11-02","arxiv_id":"2411.01336","repositories_listed":0,"syntology":null},{"url":null,"slug":"conceptfactory-facilitate-3d-object-knowledge","title":"ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization","date":"2024-11-01","arxiv_id":"2411.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-viewpoint-independent-object","title":"Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection","date":"2024-11-01","arxiv_id":"2411.00402","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-multiple-object-tracking-a-matter-of","title":"Is Multiple Object Tracking a Matter of Specialization?","date":"2024-11-01","arxiv_id":"2411.00553","repositories_listed":0,"syntology":null},{"url":null,"slug":"maroon-a-framework-for-the-joint","title":"MAROON: A Framework for the Joint Characterization of Near-Field High-Resolution Radar and Optical Depth Imaging Techniques","date":"2024-11-01","arxiv_id":"2411.00527","repositories_listed":0,"syntology":null},{"url":null,"slug":"re-thinking-richardson-lucy-without-iteration","title":"Re-thinking Richardson-Lucy without Iteration Cutoffs: Physically Motivated Bayesian Deconvolution","date":"2024-11-01","arxiv_id":"2411.00991","repositories_listed":0,"syntology":null},{"url":null,"slug":"extended-object-tracking-and-classification","title":"Extended Object Tracking and Classification based on Linear Splines","date":"2024-10-31","arxiv_id":"2410.24183","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-3d-object-detection-in-lidar-data-as","title":"HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data","date":"2024-10-31","arxiv_id":"2410.23767","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-estimation-for-3d-object","title":"Uncertainty Estimation for 3D Object Detection via Evidential Learning","date":"2024-10-31","arxiv_id":"2410.23910","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-place-solution-to-the-eccv-2024-road","title":"First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Atomic Activity Recognition 2024","date":"2024-10-30","arxiv_id":"2410.23092","repositories_listed":0,"syntology":null},{"url":null,"slug":"keypoint-abstraction-using-large-models-for","title":"Keypoint Abstraction using Large Models for Object-Relative Imitation Learning","date":"2024-10-30","arxiv_id":"2410.23254","repositories_listed":0,"syntology":null},{"url":null,"slug":"refereverything-towards-segmenting-everything","title":"ReferEverything: Towards Segmenting Everything We Can Speak of in Videos","date":"2024-10-30","arxiv_id":"2410.23287","repositories_listed":0,"syntology":null},{"url":null,"slug":"relationbooth-towards-relation-aware","title":"RelationBooth: Towards Relation-Aware Customized Object Generation","date":"2024-10-30","arxiv_id":"2410.23280","repositories_listed":0,"syntology":null},{"url":null,"slug":"s3pt-scene-semantics-and-structure-guided","title":"S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving","date":"2024-10-30","arxiv_id":"2410.23085","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-object-discovery-a-comprehensive","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","date":"2024-10-30","arxiv_id":"2411.00868","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-issues-with-working-memory-in","title":"Addressing Issues with Working Memory in Video Object Segmentation","date":"2024-10-29","arxiv_id":"2410.22451","repositories_listed":0,"syntology":null},{"url":null,"slug":"paca-perspective-aware-cross-attention","title":"PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement","date":"2024-10-29","arxiv_id":"2410.22059","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-semantic-understanding-for-real","title":"Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation","date":"2024-10-29","arxiv_id":"2410.21926","repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-object-synthesis-via-adaptive-text","title":"Novel Object Synthesis via Adaptive Text-Image Harmony","date":"2024-10-28","arxiv_id":"2410.20823","repositories_listed":0,"syntology":null},{"url":null,"slug":"taco-adversarial-camouflage-optimization-on","title":"TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors","date":"2024-10-28","arxiv_id":"2410.21443","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamics-as-prompts-in-context-learning-for","title":"Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications","date":"2024-10-27","arxiv_id":"2410.20357","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-via-language","title":"Open-Vocabulary Object Detection via Language Hierarchy","date":"2024-10-27","arxiv_id":"2410.20371","repositories_listed":0,"syntology":null},{"url":null,"slug":"give-guiding-visual-encoder-to-perceive","title":"GiVE: Guiding Visual Encoder to Perceive Overlooked Information","date":"2024-10-26","arxiv_id":"2410.20109","repositories_listed":0,"syntology":null},{"url":null,"slug":"decade-towards-designing-efficient-yet","title":"DECADE: Towards Designing Efficient-yet-Accurate Distance Estimation Modules for Collision Avoidance in Mobile Advanced Driver Assistance Systems","date":"2024-10-25","arxiv_id":"2410.19336","repositories_listed":0,"syntology":null},{"url":null,"slug":"ippon-common-sense-guided-informative-path","title":"IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation","date":"2024-10-25","arxiv_id":"2410.19697","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-rigid-relative-placement-through-3d-dense","title":"Non-rigid Relative Placement through 3D Dense Diffusion","date":"2024-10-25","arxiv_id":"2410.19247","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantics-in-robotics-environmental-data-can","title":"Semantics in Robotics: Environmental Data Can't Yield Conventions of Human Behaviour","date":"2024-10-25","arxiv_id":"2410.19308","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-3d-gaussian-tracking-for-graph-based","title":"Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling","date":"2024-10-24","arxiv_id":"2410.18912","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-global-object-centric","title":"Learning Global Object-Centric Representations via Disentangled Slot Attention","date":"2024-10-24","arxiv_id":"2410.18809","repositories_listed":0,"syntology":null}],"record_sha256":"28b5e47a13f8af3431b055f0e80d14b30aab659efa53a5c2d402a16e0debc102","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}