{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425},{"id":"2505.14362","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","created":"2025-05-20","cited_by_count":410},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2408.13257","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","created":"2024-08-23","cited_by_count":292},{"id":"2505.15966","title":"Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning","created":"2025-05-21","cited_by_count":278},{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248},{"id":"2503.06520","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","created":"2025-03-09","cited_by_count":239},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2508.11630","title":"Thyme: Think Beyond Images","created":"2025-08-15","cited_by_count":167},{"id":"2505.08617","title":"OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning","created":"2025-05-13","cited_by_count":163},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"2505.21374","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","created":"2025-05-27","cited_by_count":118},{"id":"2503.07608","title":"AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning","created":"2025-03-10","cited_by_count":108},{"id":"2505.12434","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","created":"2025-05-18","cited_by_count":93},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"id":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84},{"id":"2507.07998","title":"PyVision: Agentic Vision with Dynamic Tooling","created":"2025-07-10","cited_by_count":79},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79},{"id":"2506.11991","title":"VGR: Visual Grounded Reasoning","created":"2025-06-13","cited_by_count":73},{"id":"2312.03052","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","created":"2023-12-05","cited_by_count":66},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61},{"id":"2301.11116","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","created":"2023-01-26","cited_by_count":58},{"id":"2302.00624","title":"Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization","created":"2023-02-01","cited_by_count":55},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49},{"id":"2306.04811","title":"Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation","created":"2023-06-07","cited_by_count":47},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2303.09857","title":"Dual-path Adaptation from Image to Video Transformers","created":"2023-03-17","cited_by_count":41},{"id":"2507.20939","title":"ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts","created":"2025-07-28","cited_by_count":41},{"id":"2402.03241","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","created":"2024-02-05","cited_by_count":36},{"id":"2505.15298","title":"AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving","created":"2025-05-21","cited_by_count":35},{"id":"1811.01549","title":"StNet: Local and Global Spatial-Temporal Modeling for Action Recognition","created":"2018-11-05","cited_by_count":28},{"id":"2506.01908","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","created":"2025-06-02","cited_by_count":26},{"id":"2503.11892","title":"DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning","created":"2025-03-14","cited_by_count":24},{"id":"2508.12109","title":"Simple o3: Towards Interleaved Vision-Language Reasoning","created":"2025-08-16","cited_by_count":24},{"id":"2505.19866","title":"HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation","created":"2025-05-26","cited_by_count":18},{"id":"2412.12704","title":"MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert","created":"2024-12-17","cited_by_count":17},{"id":"2503.06456","title":"DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning","created":"2025-03-09","cited_by_count":16},{"id":"2412.19080","title":"Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation","created":"2024-12-26","cited_by_count":15},{"id":"2412.09895","title":"Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP","created":"2024-12-13","cited_by_count":9},{"id":"2502.20158","title":"Learning to Generalize without Bias for Open-Vocabulary Action Recognition","created":"2025-02-27","cited_by_count":7},{"id":"2505.03420","title":"Mitigating Image Captioning Hallucinations in Vision-Language Models","created":"2025-05-06","cited_by_count":7},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7},{"id":"2503.06847","title":"MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification","created":"2025-03-10","cited_by_count":2}],"next_cursor":null}