{"total":148,"rows":[{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406,"area":"mllm"},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363,"area":null},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190,"area":null},{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166,"area":null},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79,"area":null},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70,"area":null},{"id":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66,"area":null},{"id":"2401.02309","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2412.07744","title":"StyleMaster: Stylize Your Video with Artistic Generation and Translation","created":"2024-12-10","cited_by_count":47,"area":null},{"id":"2503.13444","title":"VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning","created":"2025-03-17","cited_by_count":43,"area":"lr"},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2404.00801","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","created":"2024-03-31","cited_by_count":34,"area":null},{"id":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31,"area":null},{"id":"2407.15051","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","created":"2024-07-21","cited_by_count":30,"area":null},{"id":"2312.00083","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","created":"2023-11-30","cited_by_count":29,"area":null},{"id":"2312.12155","title":"Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval","created":"2023-12-19","cited_by_count":27,"area":null},{"id":"2506.18883","title":"Universal Video Temporal Grounding with Generative Multi-modal Large Language Models","created":"2025-06-23","cited_by_count":27,"area":"mllm"},{"id":"2404.01174","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","created":"2024-04-01","cited_by_count":25,"area":"ssm"},{"id":"2404.09263","title":"Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection","created":"2024-04-14","cited_by_count":25,"area":null},{"id":"2412.13441","title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","created":"2024-12-18","cited_by_count":23,"area":null},{"id":"2410.01615","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2402.09444","title":"Multimodal Action Quality Assessment","created":"2024-01-31","cited_by_count":20,"area":null},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2403.02076","title":"VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT","created":"2024-03-04","cited_by_count":19,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2406.18113","title":"Chrono: A Simple Blueprint for Representing Time in MLLMs","created":"2024-06-26","cited_by_count":18,"area":"mllm"},{"id":"2411.14901","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","created":"2024-11-22","cited_by_count":18,"area":"mllm"},{"id":"2509.24734","title":"A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2402.15490","title":"A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends","created":"2024-02-23","cited_by_count":16,"area":null},{"id":"2404.04933","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2312.06729","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","created":"2023-12-11","cited_by_count":15,"area":null},{"id":"2312.17117","title":"Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videos","created":"2023-12-28","cited_by_count":14,"area":"lr"},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14,"area":"moe"},{"id":"2310.05241","title":"SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval","created":"2023-10-08","cited_by_count":13,"area":null},{"id":"2403.14174","title":"Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding","created":"2024-03-21","cited_by_count":12,"area":null},{"id":"2510.17023","title":"Enrich and Detect: Video Temporal Grounding with Multimodal LLMs","created":"2025-10-19","cited_by_count":12,"area":"mllm"},{"id":"2312.02549","title":"DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2304.02934","title":"Boundary-Denoising for Video Activity Localization","created":"2023-04-06","cited_by_count":10,"area":null},{"id":"2408.16272","title":"Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding","created":"2024-08-29","cited_by_count":10,"area":null},{"id":"2502.08544","title":"Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval","created":"2025-02-12","cited_by_count":10,"area":null},{"id":"2405.12540","title":"Context-Enhanced Video Moment Retrieval with Large Language Models","created":"2024-05-21","cited_by_count":9,"area":null},{"id":"2504.07519","title":"VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2501.10787","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2504.13035","title":"Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval","created":"2025-04-17","cited_by_count":8,"area":null},{"id":"2512.03963","title":"TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning","created":"2025-12-03","cited_by_count":8,"area":"mllm"},{"id":"2210.05242","title":"Leveraging the Video-level Semantic Consistency of Event for Audio-visual Event Localization","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2211.02178","title":"Zero-shot Video Moment Retrieval With Off-the-Shelf Models","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2410.13598","title":"Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2511.21331","title":"The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment","created":"2025-11-26","cited_by_count":7,"area":null},{"id":"2302.08063","title":"MINOTAUR: Multi-task Video Grounding From Multimodal Queries","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2403.01437","title":"GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features","created":"2024-03-03","cited_by_count":6,"area":null},{"id":"2404.01745","title":"Unleash the Potential of CLIP for Video Highlight Detection","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2406.00143","title":"Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding","created":"2024-05-31","cited_by_count":6,"area":null},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2407.13933","title":"Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence","created":"2024-07-18","cited_by_count":6,"area":null},{"id":"2503.09949","title":"UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2402.13576","title":"Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2411.19941","title":"Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark","created":"2024-11-29","cited_by_count":5,"area":null},{"id":"2501.10692","title":"Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection","created":"2025-01-18","cited_by_count":5,"area":null},{"id":"2505.12154","title":"Learning to Highlight Audio by Watching Movies","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2604.14149","title":"One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding","created":"2026-04-15","cited_by_count":5,"area":"mllm"},{"id":"2207.01814","title":"Multimodal Frame-Scoring Transformer for Video Summarization","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2303.14768","title":"Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies","created":"2023-03-26","cited_by_count":4,"area":null},{"id":"2402.12079","title":"LVCHAT: Facilitating Long Video Comprehension","created":"2024-02-19","cited_by_count":4,"area":"mllm"},{"id":"2504.02286","title":"Moment Quantization for Video Temporal Grounding","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2506.18071","title":"MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering","created":"2025-06-22","cited_by_count":4,"area":"agents"},{"id":"2509.23867","title":"Sim-DETR: Unlock DETR for Temporal Sentence Grounding","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2510.20244","title":"Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2602.08099","title":"VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval","created":"2026-02-08","cited_by_count":4,"area":"mllm"},{"id":"2602.09507","title":"Towards Uniformity and Alignment for Multimodal Representation Learning","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2603.24934","title":"CVA: Context-aware Video-text Alignment for Video Temporal Grounding","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2606.06294","title":"Towards One-to-Many Temporal Grounding","created":"2026-06-04","cited_by_count":4,"area":null},{"id":"2407.05118","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","created":"2024-07-06","cited_by_count":3,"area":null},{"id":"2411.02851","title":"Learning to Unify Audio, Visual and Text for Audio-Enhanced Multilingual Visual Answer Localization","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2412.01558","title":"VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval","created":"2024-12-02","cited_by_count":3,"area":"mllm"},{"id":"2501.07305","title":"The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2503.00364","title":"CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion","created":"2025-03-01","cited_by_count":3,"area":null},{"id":"2504.01792","title":"UniViTAR: Unified Vision Transformer with Native Resolution","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2506.21028","title":"TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2507.04958","title":"Boosting Temporal Sentence Grounding via Causal Inference","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2601.23232","title":"ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2305.18724","title":"Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2308.15109","title":"DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection","created":"2023-08-29","cited_by_count":2,"area":"diffusion"},{"id":"2312.06950","title":"READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2401.13329","title":"Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval","created":"2024-01-24","cited_by_count":2,"area":"diffusion"},{"id":"2408.06622","title":"ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2503.06820","title":"Towards Fine-Grained Video Question Answering","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2503.09027","title":"Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs","created":"2025-03-12","cited_by_count":2,"area":null}],"next_cursor":"100"}