{"total":103,"rows":[{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167,"area":"diffusion"},{"id":"2406.08394","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","created":"2024-06-12","cited_by_count":137,"area":"mllm"},{"id":"2401.00896","title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","created":"2023-12-31","cited_by_count":91,"area":"diffusion"},{"id":"2401.02400","title":"Learning the 3D Fauna of the Web","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56,"area":null},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2503.10076","title":"VMBench: A Benchmark for Perception-Aligned Video Motion Generation","created":"2025-03-13","cited_by_count":49,"area":null},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43,"area":null},{"id":"2306.00576","title":"MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding","created":"2023-06-01","cited_by_count":36,"area":null},{"id":"2310.16447","title":"ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors","created":"2023-10-25","cited_by_count":24,"area":null},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2401.13554","title":"PanAf20K: A Large Video Dataset for Wild Ape Detection and Behaviour Recognition","created":"2024-01-24","cited_by_count":22,"area":null},{"id":"2310.08530","title":"X-Pose: Detecting Any Keypoints","created":"2023-10-12","cited_by_count":21,"area":null},{"id":"2412.00837","title":"AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer","created":"2024-12-01","cited_by_count":20,"area":null},{"id":"2303.13174","title":"3D-POP -- An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture","created":"2023-03-23","cited_by_count":18,"area":null},{"id":"2404.12347","title":"AniClipart: Clipart Animation with Text-to-Video Priors","created":"2024-04-18","cited_by_count":17,"area":null},{"id":"2412.02186","title":"VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding","created":"2024-12-03","cited_by_count":17,"area":"lr"},{"id":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2405.17698","title":"BaboonLand Dataset: Tracking Primates in the Wild and Automating Behaviour Recognition from Drone Videos","created":"2024-05-27","cited_by_count":14,"area":null},{"id":"2503.18223","title":"MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps","created":"2025-03-23","cited_by_count":14,"area":null},{"id":"2207.10553","title":"MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2511.01169","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction","created":"2025-11-03","cited_by_count":9,"area":null},{"id":"2307.10763","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2312.15612","title":"APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond","created":"2023-12-25","cited_by_count":8,"area":null},{"id":"2308.09953","title":"UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning","created":"2023-08-19","cited_by_count":7,"area":null},{"id":"2408.12930","title":"Animal Identification with Independent Foreground and Background Modeling","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2508.00298","title":"AniMer+: Unified Pose and Shape Estimation Across Mammalia and Aves via Family-Aware Transformer","created":"2025-08-01","cited_by_count":7,"area":null},{"id":"2511.15622","title":"The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification","created":"2025-11-19","cited_by_count":7,"area":null},{"id":"2310.13483","title":"Application of deep learning for livestock behaviour recognition: A systematic literature review","created":"2023-10-20","cited_by_count":5,"area":null},{"id":"2312.08764","title":"CattleEyeView: A Multi-task Top-down View Cattle Dataset for Smarter Precision Livestock Farming","created":"2023-12-14","cited_by_count":5,"area":null},{"id":"2410.17136","title":"AlphaChimp: Tracking and Behavior Recognition of Chimpanzees","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2502.21201","title":"The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2512.03350","title":"SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2606.02522","title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","created":"2026-06-01","cited_by_count":5,"area":"mllm"},{"id":"2304.04175","title":"Token Boosting for Robust Self-Supervised Visual Transformer Pre-training","created":"2023-04-09","cited_by_count":4,"area":null},{"id":"2305.16555","title":"CVB: A Video Dataset of Cattle Visual Behaviors","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2405.14002","title":"Animal Behavior Analysis Methods Using Deep Learning: A Survey","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2406.09647","title":"OpenAnimalTracks: A Dataset for Animal Track Recognition","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2501.08931","title":"Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos","created":"2025-01-15","cited_by_count":4,"area":null},{"id":"2504.05706","title":"SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2510.24117","title":"DogMo: A Large-Scale Multi-View RGB-D Dataset for 4D Canine Motion Recovery","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2407.18289","title":"MARINE: A Computer Vision Model for Detecting Rare Predator-Prey Interactions in Animal Videos","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2502.18214","title":"Learning Structure-Supporting Dependencies via Keypoint Interactive Transformer for General Mammal Pose Estimation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2503.16120","title":"Probabilistic Prompt Distribution Learning for Animal Pose Estimation","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2503.18712","title":"LLaVAction: evaluating and training multi-modal large language models for action understanding","created":"2025-03-24","cited_by_count":3,"area":"mllm"},{"id":"2506.21476","title":"Global and Local Entailment Learning for Natural World Imagery","created":"2025-06-26","cited_by_count":3,"area":"mllm"},{"id":"2508.21052","title":"FakeParts: a New Family of AI-Generated DeepFakes","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2410.09312","title":"Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2412.04273","title":"Reinforcement Learning from Wild Animal Videos","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2507.02713","title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation","created":"2025-07-03","cited_by_count":2,"area":"diffusion"},{"id":"2508.16062","title":"Advances and Trends in the 3D Reconstruction of the Shape and Motion of Animals","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2605.07604","title":"SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2211.08634","title":"Semantic keypoint extraction for scanned animals using multi-depth-camera systems","created":"2022-11-16","cited_by_count":1,"area":null},{"id":"2306.11326","title":"Meerkat Behaviour Recognition Dataset","created":"2023-06-20","cited_by_count":1,"area":null},{"id":"2309.13086","title":"Towards Lexical Analysis of Dog Vocalizations via Online Videos","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2406.14412","title":"Benchmarking Monocular 3D Dog Pose Estimation Using In-The-Wild Motion Capture Data","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2505.02825","title":"Towards Application-Specific Evaluation of Vision Models: Case Studies in Ecology and Biology","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2507.02403","title":"Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2507.11985","title":"Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2507.20240","title":"AnimalClue: Recognizing Animals by their Traces","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2508.08783","title":"DiffPose-Animal: A Language-Conditioned Diffusion Framework for Animal Pose Estimation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.21291","title":"VC-Agent: An Interactive Agent for Customized Video Dataset Collection","created":"2025-09-25","cited_by_count":1,"area":"agents"},{"id":"2511.04255","title":"MedSapiens: Taking a Pose to Rethink Medical Imaging Landmark Detection","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2512.12287","title":"RealDrag: The First Dragging Benchmark with Real Target Image","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2512.21126","title":"MarineEval: Assessing the Marine Intelligence of Vision-Language Models","created":"2025-12-24","cited_by_count":1,"area":"mllm"},{"id":"2602.19874","title":"BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.03714","title":"Order Is Not Layout: Order-to-Space Bias in Image Generation","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.16816","title":"WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.14569","title":"Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.09876","title":"Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2607.10287","title":"InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2609.01823","title":"Kirin: Animal Motion Generation from In-the-Wild Video","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2405.05523","title":"Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training","created":"2024-05-09","cited_by_count":0,"area":null},{"id":"2405.20025","title":"From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehave","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2406.07742","title":"C3DAG: Controlled 3D Animal Generation using 3D pose guidance","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2406.16273","title":"YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals","created":"2024-06-24","cited_by_count":0,"area":"diffusion"},{"id":"2504.00394","title":"AP-CAP: Advancing High-Quality Data Synthesis for Animal Pose Estimation via a Controllable Image Generation Pipeline","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2505.15408","title":"Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.16633","title":"Towards Texture- And Shape-Independent 3D Keypoint Estimation in Birds","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2505.21589","title":"Do you see what I see? An Ambiguous Optical Illusion Dataset exposing limitations of Explainable AI","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2505.24253","title":"Interactive Video Generation via Domain Adaptation","created":"2025-05-30","cited_by_count":0,"area":"diffusion"},{"id":"2506.01214","title":"A Review on Coarse to Fine-Grained Animal Action Recognition","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2507.07994","title":"Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2507.11102","title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model","created":"2025-07-15","cited_by_count":0,"area":"mllm"},{"id":"2509.16141","title":"AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2511.20809","title":"Layer-Aware Video Composition via Split-then-Merge","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.16133","title":"Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.09518","title":"A Universal Action Space for General Behavior Analysis","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.19672","title":"Making Video Models Adhere to User Intent with Minor Adjustments","created":"2026-03-20","cited_by_count":0,"area":"diffusion"},{"id":"2603.23883","title":"BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.25524","title":"CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2603.26780","title":"RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2607.00752","title":"GKDT: General Keypoint Detection Transformer","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.02269","title":"AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2607.17399","title":"The PanAf-SBR Dataset: Social Behaviour Recognition for Wild Great Apes","created":"2026-07-19","cited_by_count":0,"area":null}],"next_cursor":"100"}