{"total":86,"rows":[{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","cited_by_count":90,"area":null},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52,"area":null},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49,"area":null},{"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":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2211.12764","title":"VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval","created":"2022-11-23","cited_by_count":36,"area":null},{"id":"2211.09623","title":"Cross-Modal Adapter for Vision-Language Retrieval","created":"2022-11-17","cited_by_count":35,"area":null},{"id":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35,"area":null},{"id":"2403.10254","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","created":"2024-03-15","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":"2401.10588","title":"DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval","created":"2024-01-19","cited_by_count":26,"area":null},{"id":"2403.16997","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","created":"2024-03-25","cited_by_count":26,"area":null},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2212.03490","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","created":"2022-12-07","cited_by_count":21,"area":null},{"id":"2307.12964","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","created":"2023-07-24","cited_by_count":21,"area":null},{"id":"2310.11612","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","created":"2023-10-17","cited_by_count":20,"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":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"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":"2412.19178","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","created":"2024-12-26","cited_by_count":13,"area":null},{"id":"2401.00701","title":"Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning","created":"2024-01-01","cited_by_count":12,"area":null},{"id":"2503.10111","title":"Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2311.15769","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","created":"2023-11-27","cited_by_count":11,"area":null},{"id":"2309.11082","title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2312.00347","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2504.02397","title":"Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval","created":"2025-04-03","cited_by_count":8,"area":null},{"id":"2208.12510","title":"PRVR: Partially Relevant Video Retrieval","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2301.01953","title":"Learning Trajectory-Word Alignments for Video-Language Tasks","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2302.09473","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","created":"2023-02-19","cited_by_count":7,"area":null},{"id":"2311.00298","title":"An Empirical Study of Frame Selection for Text-to-Video Retrieval","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2404.14066","title":"SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrieval","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2409.19865","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","created":"2024-09-30","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":"2305.07910","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2403.14870","title":"VidLA: Video-Language Alignment at Scale","created":"2024-03-21","cited_by_count":5,"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":"2408.00096","title":"From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2408.07249","title":"Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2507.02316","title":"Are Synthetic Videos Useful? A Benchmark for Retrieval-Centric Evaluation of Synthetic Videos","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2507.15504","title":"Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization","created":"2025-07-21","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":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2502.02885","title":"Expertized Caption Auto-Enhancement for Video-Text Retrieval","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2509.04773","title":"Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2308.05550","title":"Cross-Domain Product Representation Learning for Rich-Content E-Commerce","created":"2023-08-10","cited_by_count":3,"area":null},{"id":"2311.15075","title":"Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding","created":"2023-11-25","cited_by_count":3,"area":null},{"id":"2404.05083","title":"DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models","created":"2024-04-07","cited_by_count":3,"area":null},{"id":"2405.12710","title":"Text-Video Retrieval with Global-Local Semantic Consistent Learning","created":"2024-05-21","cited_by_count":3,"area":null},{"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":"2210.08452","title":"Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames","created":"2022-10-16","cited_by_count":2,"area":null},{"id":"2303.05707","title":"MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2307.09972","title":"Fine-grained Text-Video Retrieval with Frozen Image Encoders","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2401.12419","title":"Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews)","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2404.12216","title":"ProTA: Probabilistic Token Aggregation for Text-Video Retrieval","created":"2024-04-18","cited_by_count":2,"area":null},{"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":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2511.12834","title":"SAGA: Source Attribution of Generative AI Videos","created":"2025-11-16","cited_by_count":2,"area":null},{"id":"2303.16341","title":"Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2307.10567","title":"No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2308.01217","title":"TeachCLIP: Multi-Grained Teaching for Efficient Text-to-Video Retrieval","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2309.09531","title":"Decompose Semantic Shifts for Composed Image Retrieval","created":"2023-09-18","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":"2410.12407","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","created":"2024-10-16","cited_by_count":1,"area":null},{"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":"2510.10180","title":"TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2510.21798","title":"An Evaluation of Hybrid Annotation Workflows on High-Ambiguity Spatiotemporal Video Footage","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.01312","title":"IVCR-200K: A Large-Scale Multi-turn Dialogue Benchmark for Interactive Video Corpus Retrieval","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2607.00446","title":"VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2508.01711","title":"GAIS: Frame-Level Gated Audio-Visual Integration with Semantic Variance-Scaled Perturbation for Text-Video Retrieval","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2508.02340","title":"Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.14812","title":"Repeating Words for Video-Language Retrieval with Coarse-to-Fine Objectives","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2510.06512","title":"LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.15470","title":"MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval","created":"2025-10-17","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":"2603.08224","title":"SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.20851","title":"Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2609.29721","title":"SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}