{"total":57,"rows":[{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"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":"2410.07348","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts","created":"2024-10-09","cited_by_count":56,"area":"moe"},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55,"area":"mllm"},{"id":"2303.09867","title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","created":"2023-03-17","cited_by_count":52,"area":"diffusion"},{"id":"2303.14369","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","created":"2023-03-25","cited_by_count":45,"area":null},{"id":"2311.01015","title":"Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs","created":"2023-11-02","cited_by_count":45,"area":"diffusion"},{"id":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"area":"moe"},{"id":"2409.01156","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","created":"2024-09-02","cited_by_count":40,"area":"inference"},{"id":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35,"area":null},{"id":"2403.17998","title":"Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval","created":"2024-03-26","cited_by_count":33,"area":null},{"id":"2305.12218","title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment","created":"2023-05-20","cited_by_count":32,"area":null},{"id":"2303.07216","title":"Parallel Vertex Diffusion for Unified Visual Grounding","created":"2023-03-13","cited_by_count":28,"area":"diffusion"},{"id":"2310.19001","title":"Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation","created":"2023-10-29","cited_by_count":27,"area":null},{"id":"2503.19009","title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","created":"2025-03-24","cited_by_count":20,"area":null},{"id":"2401.15652","title":"Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2410.11619","title":"MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval","created":"2024-10-15","cited_by_count":17,"area":null},{"id":"2403.00691","title":"Tri-Modal Motion Retrieval by Learning a Joint Embedding Space","created":"2024-03-01","cited_by_count":16,"area":null},{"id":"2405.19465","title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter","created":"2024-05-29","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":"2306.13337","title":"Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning","created":"2023-06-23","cited_by_count":14,"area":null},{"id":"2601.16155","title":"HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval","created":"2026-01-22","cited_by_count":14,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2405.13824","title":"GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2407.10528","title":"Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation","created":"2024-07-15","cited_by_count":10,"area":"diffusion"},{"id":"2302.11799","title":"FiTs: Fine-grained Two-stage Training for Knowledge-aware Question Answering","created":"2023-02-23","cited_by_count":8,"area":null},{"id":"2503.20698","title":"MMMORRF: Multimodal Multilingual Modularized Reciprocal Rank Fusion","created":"2025-03-26","cited_by_count":8,"area":"mllm"},{"id":"2305.18158","title":"Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning","created":"2023-05-29","cited_by_count":7,"area":null},{"id":"2408.10575","title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval","created":"2024-08-20","cited_by_count":7,"area":"ssm"},{"id":"2305.10049","title":"TG-VQA: Ternary Game of Video Question Answering","created":"2023-05-17","cited_by_count":6,"area":null},{"id":"2503.10526","title":"NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2407.16394","title":"SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2306.16533","title":"ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2308.02339","title":"Improving Scene Graph Generation with Superpixel-Based Interaction Learning","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2409.02371","title":"Unfolding Videos Dynamics via Taylor Expansion","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2410.01261","title":"OCC-MLLM:Empowering Multimodal Large Language Model For the Understanding of Occluded Objects","created":"2024-10-02","cited_by_count":3,"area":"mllm"},{"id":"2503.17417","title":"Generative Modeling of Class Probability for Multi-Modal Representation Learning","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2509.01383","title":"Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2512.16925","title":"V-Agent: An Interactive Video Search System Using Vision-Language Models","created":"2025-11-04","cited_by_count":3,"area":"mllm"},{"id":"2410.06618","title":"Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2501.18269","title":"MAMS: Model-Agnostic Module Selection Framework for Video Captioning","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2506.03589","title":"BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2212.05262","title":"Position Embedding Needs an Independent Layer Normalization","created":"2022-12-10","cited_by_count":1,"area":null},{"id":"2311.02122","title":"Lost Your Style? Navigating with Semantic-Level Approach for Text-to-Outfit Retrieval","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2410.01861","title":"OCC-MLLM-Alpha:Empowering Multi-modal Large Language Model for the Understanding of Occluded Objects with Self-Supervised Test-Time Learning","created":"2024-10-02","cited_by_count":1,"area":"mllm"},{"id":"2504.01591","title":"Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2505.12499","title":"Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2508.06964","title":"Adversarial Video Promotion Against Text-to-Video Retrieval","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2609.00551","title":"EM^2Mem: Event-Centric Multimodal Memory for Large Language Models","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2505.24346","title":"VUDG: A Dataset for Video Understanding Domain Generalization","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2510.21806","title":"Frame-Difference Guided Dynamic Region Perception for CLIP Adaptation in Text-Video Retrieval","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.25267","title":"EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2605.00826","title":"Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis","created":"2026-03-07","cited_by_count":0,"area":null}],"next_cursor":null}