{"list":"other","total":68,"rows":[{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146},{"id":"2406.19389","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","created":"2024-06-27","cited_by_count":127},{"id":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2404.13013","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","created":"2024-04-19","cited_by_count":119},{"id":"2001.06891","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","created":"2020-01-19","cited_by_count":118},{"id":"2410.19702","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","created":"2024-10-25","cited_by_count":106},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97},{"id":"2106.11013","title":"Interventional Video Grounding with Dual Contrastive Learning","created":"2021-06-21","cited_by_count":94},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89},{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","cited_by_count":86},{"id":"2405.13382","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","created":"2024-05-22","cited_by_count":85},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65},{"id":"2403.04593","title":"Embodied Understanding of Driving Scenarios","created":"2024-03-07","cited_by_count":63},{"id":"2410.12813","title":"ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models","created":"2024-10-01","cited_by_count":54},{"id":"2107.05624","title":"End-to-end Multi-modal Video Temporal Grounding","created":"2021-07-12","cited_by_count":47},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37},{"id":"2407.21534","title":"ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models","created":"2024-07-31","cited_by_count":33},{"id":"2409.20365","title":"VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs","created":"2024-09-30","cited_by_count":29},{"id":"2408.16219","title":"Training-free Video Temporal Grounding using Large-scale Pre-trained Models","created":"2024-08-29","cited_by_count":28},{"id":"2412.09616","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","created":"2024-12-12","cited_by_count":28},{"id":"2405.03194","title":"CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenario","created":"2024-05-06","cited_by_count":27},{"id":"2403.02076","title":"VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT","created":"2024-03-04","cited_by_count":19},{"id":"2501.04336","title":"Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs","created":"2025-01-08","cited_by_count":19},{"id":"2502.11664","title":"VRoPE: Rotary Position Embedding for Video Large Language Models","created":"2025-02-17","cited_by_count":18},{"id":"2501.08326","title":"Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks","created":"2025-01-14","cited_by_count":17},{"id":"2502.12370","title":"Positional Encoding in Transformer-Based Time Series Models: A Survey","created":"2025-02-17","cited_by_count":14},{"id":"2411.16932","title":"Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding","created":"2024-11-25","cited_by_count":12},{"id":"2510.14672","title":"VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning","created":"2025-10-16","cited_by_count":12},{"id":"2510.17023","title":"Enrich and Detect: Video Temporal Grounding with Multimodal LLMs","created":"2025-10-19","cited_by_count":12},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9},{"id":"2509.15178","title":"Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding","created":"2025-09-18","cited_by_count":9},{"id":"2501.02385","title":"Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variations","created":"2025-01-04","cited_by_count":7},{"id":"2508.07925","title":"TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding","created":"2025-08-11","cited_by_count":7},{"id":"2307.02682","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment","created":"2023-07-05","cited_by_count":4},{"id":"2407.08443","title":"Infinite Motion: Extended Motion Generation via Long Text Instructions","created":"2024-07-11","cited_by_count":4},{"id":"2408.01669","title":"SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses","created":"2024-08-03","cited_by_count":4},{"id":"2403.16539","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","created":"2024-03-25","cited_by_count":3},{"id":"2507.15569","title":"DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding","created":"2025-07-21","cited_by_count":3}],"next_cursor":null}