{"total":280,"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":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"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":"2406.15252","title":"VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation","created":"2024-06-21","cited_by_count":197,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"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":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119,"area":"mllm"},{"id":"2308.05095","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","created":"2023-08-09","cited_by_count":92,"area":"diffusion"},{"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":"2312.12470","title":"Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation","created":"2023-12-19","cited_by_count":76,"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":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"area":null},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2309.07439","title":"DePT: Decoupled Prompt Tuning","created":"2023-09-14","cited_by_count":58,"area":null},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55,"area":"mllm"},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"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":"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":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49,"area":null},{"id":"2401.10090","title":"Cross-Modality Perturbation Synergy Attack for Person Re-identification","created":"2024-01-18","cited_by_count":45,"area":null},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2501.19252","title":"Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search","created":"2025-01-31","cited_by_count":41,"area":"diffusion"},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37,"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":"2308.16632","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","created":"2023-08-31","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":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35,"area":null},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33,"area":null},{"id":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32,"area":null},{"id":"2310.16640","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","created":"2023-10-25","cited_by_count":31,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28,"area":null},{"id":"2403.07938","title":"Text-to-Audio Generation Synchronized with Videos","created":"2024-03-08","cited_by_count":28,"area":"diffusion"},{"id":"2508.07901","title":"Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation","created":"2025-08-11","cited_by_count":28,"area":null},{"id":"2302.06098","title":"Towards Local Visual Modeling for Image Captioning","created":"2023-02-13","cited_by_count":26,"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":"2403.16997","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","created":"2024-03-25","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":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2409.19291","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","created":"2024-09-28","cited_by_count":23,"area":"moe"},{"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":"2405.07472","title":"GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting","created":"2024-05-13","cited_by_count":22,"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":"2311.00519","title":"REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning","created":"2023-11-01","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":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2407.05363","title":"Multi-branch Collaborative Learning Network for 3D Visual Grounding","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2411.02327","title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","created":"2024-11-04","cited_by_count":20,"area":"inference"},{"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":"2305.12903","title":"DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment","created":"2023-05-22","cited_by_count":19,"area":"diffusion"},{"id":"2501.00513","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","created":"2024-12-31","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":"2407.20664","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","created":"2024-07-30","cited_by_count":18,"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":"2308.05359","title":"Pseudo-label Alignment for Semi-supervised Instance Segmentation","created":"2023-08-10","cited_by_count":17,"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":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"area":null},{"id":"2306.10169","title":"Meta-Personalizing Vision-Language Models to Find Named Instances in Video","created":"2023-06-16","cited_by_count":16,"area":"mllm"},{"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":"2407.01872","title":"Referring Atomic Video Action Recognition","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2501.01950","title":"MADGEN: Mass-Spec attends to De Novo Molecular generation","created":"2025-01-03","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":"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":"2411.14452","title":"Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2308.15226","title":"CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation","created":"2023-08-29","cited_by_count":14,"area":null},{"id":"2312.04248","title":"TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes","created":"2023-12-07","cited_by_count":14,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2507.00950","title":"MVP: Winning Solution to SMP Challenge 2025 Video Track","created":"2025-07-01","cited_by_count":14,"area":null},{"id":"2301.03160","title":"Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network","created":"2023-01-09","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":"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":"2308.02982","title":"Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation","created":"2023-08-06","cited_by_count":12,"area":"mllm"},{"id":"2308.10402","title":"Simple Baselines for Interactive Video Retrieval with Questions and Answers","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2312.02914","title":"Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training","created":"2023-12-05","cited_by_count":12,"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":"2404.11614","title":"Dynamic Typography: Bringing Text to Life via Video Diffusion Prior","created":"2024-04-17","cited_by_count":12,"area":"diffusion"},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2605.22344","title":"Bernini: Latent Semantic Planning for Video Diffusion","created":"2026-05-21","cited_by_count":12,"area":"lr"},{"id":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2504.03970","title":"VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models","created":"2025-04-04","cited_by_count":11,"area":"mllm"},{"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":"2407.02309","title":"Semantically Guided Representation Learning For Action Anticipation","created":"2024-07-02","cited_by_count":10,"area":null},{"id":"2408.12023","title":"Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2503.05186","title":"Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions","created":"2025-03-07","cited_by_count":10,"area":"mllm"},{"id":"2506.07471","title":"Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval","created":"2025-06-09","cited_by_count":10,"area":null},{"id":"2508.09486","title":"Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2401.03522","title":"Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videos","created":"2024-01-07","cited_by_count":9,"area":null},{"id":"2412.07183","title":"Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2503.20502","title":"MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning","created":"2025-03-26","cited_by_count":9,"area":"mllm"},{"id":"2506.02439","title":"Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2510.27571","title":"Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2511.22989","title":"MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation","created":"2025-11-28","cited_by_count":9,"area":null}],"next_cursor":"100"}