{"total":103,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280,"area":null},{"id":"2109.04290","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","created":"2021-09-09","cited_by_count":116,"area":"moe"},{"id":"2207.07852","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","created":"2022-07-16","cited_by_count":104,"area":null},{"id":"2303.17393","title":"Dynamic Conceptional Contrastive Learning for Generalized Category Discovery","created":"2023-03-30","cited_by_count":92,"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":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79,"area":null},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71,"area":"mllm"},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2211.11427","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","created":"2022-11-21","cited_by_count":57,"area":null},{"id":"2303.09867","title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","created":"2023-03-17","cited_by_count":52,"area":"diffusion"},{"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":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44,"area":null},{"id":"2303.08409","title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","created":"2023-03-15","cited_by_count":40,"area":null},{"id":"2204.02874","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","created":"2022-04-06","cited_by_count":39,"area":null},{"id":"2208.14365","title":"Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search","created":"2022-08-30","cited_by_count":38,"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":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"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":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28,"area":null},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"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":"2307.12545","title":"Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2601.12768","title":"Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval","created":"2026-01-19","cited_by_count":23,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"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":"2503.19009","title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","created":"2025-03-24","cited_by_count":20,"area":null},{"id":"2207.00383","title":"ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022","created":"2022-07-01","cited_by_count":19,"area":null},{"id":"2207.09966","title":"Temporal and cross-modal attention for audio-visual zero-shot learning","created":"2022-07-20","cited_by_count":19,"area":null},{"id":"2407.16714","title":"Masked Graph Learning with Recurrent Alignment for Multimodal Emotion Recognition in Conversation","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2301.12644","title":"Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval","created":"2023-01-30","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":"2405.19465","title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter","created":"2024-05-29","cited_by_count":16,"area":null},{"id":"2302.12552","title":"Deep Learning for Video-Text Retrieval: a Review","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15,"area":null},{"id":"2111.09276","title":"Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval","created":"2021-11-17","cited_by_count":13,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2409.19961","title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","created":"2024-09-30","cited_by_count":13,"area":"mllm"},{"id":"2105.14897","title":"Connecting Language and Vision for Natural Language-Based Vehicle Retrieval","created":"2021-05-31","cited_by_count":12,"area":null},{"id":"2112.01368","title":"ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors","created":"2021-12-02","cited_by_count":12,"area":null},{"id":"2201.03639","title":"Multi-Query Video Retrieval","created":"2022-01-10","cited_by_count":11,"area":null},{"id":"2209.11388","title":"LGDN: Language-Guided Denoising Network for Video-Language Modeling","created":"2022-09-23","cited_by_count":11,"area":null},{"id":"2303.13800","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","created":"2023-03-24","cited_by_count":10,"area":null},{"id":"2110.15609","title":"BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval","created":"2021-10-29","cited_by_count":8,"area":null},{"id":"2202.03384","title":"Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval","created":"2022-02-07","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":"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":"2110.12812","title":"Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval","created":"2021-10-25","cited_by_count":6,"area":null},{"id":"2203.08688","title":"Learning video retrieval models with relevance-aware online mining","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2204.13001","title":"Relevance-based Margin for Contrastively-trained Video Retrieval Models","created":"2022-04-27","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":"2212.06206","title":"Contextual Explainable Video Representation: Human Perception-based Understanding","created":"2022-12-12","cited_by_count":5,"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":"2306.08325","title":"GCformer: An Efficient Framework for Accurate and Scalable Long-Term Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2309.08928","title":"In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval","created":"2023-09-16","cited_by_count":5,"area":"mllm"},{"id":"2402.13576","title":"Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2407.16777","title":"A Dataset for Crucial Object Recognition in Blind and Low-Vision Individuals' Navigation","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2407.18552","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","created":"2024-07-26","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":"2111.05814","title":"SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval","created":"2021-11-10","cited_by_count":4,"area":null},{"id":"2402.13566","title":"Event-aware Video Corpus Moment Retrieval","created":"2024-02-21","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":"2210.04341","title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2307.13250","title":"Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2201.06304","title":"Action Keypoint Network for Efficient Video Recognition","created":"2022-01-17","cited_by_count":2,"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":"2404.12216","title":"ProTA: Probabilistic Token Aggregation for Text-Video Retrieval","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2406.13092","title":"Multilingual Synopses of Movie Narratives: A Dataset for Vision-Language Story Understanding","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2505.06557","title":"Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2506.03473","title":"MamFusion: Multi-Mamba with Temporal Fusion for Partially Relevant Video Retrieval","created":"2025-06-04","cited_by_count":2,"area":"ssm"},{"id":"2509.26227","title":"Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.15543","title":"MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2208.07664","title":"M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval","created":"2022-08-16","cited_by_count":1,"area":null},{"id":"2309.03869","title":"Text-to-feature diffusion for audio-visual few-shot learning","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2311.06553","title":"Visual Commonsense based Heterogeneous Graph Contrastive Learning","created":"2023-11-11","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":"2412.20162","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","created":"2024-12-28","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":"2505.23952","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2508.15439","title":"Aligning Moments in Time using Video Queries","created":"2025-08-21","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":"2204.10938","title":"A Multi-level Alignment Training Scheme for Video-and-Language Grounding","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2301.13606","title":"Multi-video Moment Ranking with Multimodal Clue","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2406.13809","title":"Towards Holistic Language-video Representation: the language model-enhanced MSR-Video to Text Dataset","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2406.16111","title":"Multi-Scale Temporal Difference Transformer for Video-Text Retrieval","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2407.11677","title":"Video-Language Alignment via Spatio-Temporal Graph Transformer","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2501.06224","title":"Detection, Retrieval, and Explanation Unified: A Violence Detection System Based on Knowledge Graphs and GAT","created":"2025-01-07","cited_by_count":0,"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":"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":"2601.12010","title":"SMc2f: Robust Scenario Mining for Robotic Autonomy from Coarse to Fine","created":"2026-01-17","cited_by_count":0,"area":null}],"next_cursor":"100"}