{"total":225,"rows":[{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353,"area":null},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317,"area":"mllm"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254,"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":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191,"area":null},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182,"area":null},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159,"area":"mllm"},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131,"area":"diffusion"},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"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":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"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":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"area":null},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"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":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"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":"2203.07111","title":"Disentangled Representation Learning for Text-Video Retrieval","created":"2022-03-14","cited_by_count":77,"area":null},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74,"area":null},{"id":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2210.03114","title":"CLIP model is an Efficient Continual Learner","created":"2022-10-06","cited_by_count":65,"area":null},{"id":"2207.09248","title":"Don't Stop Learning: Towards Continual Learning for the CLIP Model","created":"2022-07-19","cited_by_count":61,"area":null},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2301.11116","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2503.10200","title":"LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents","created":"2025-03-13","cited_by_count":58,"area":"agents"},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55,"area":null},{"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":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52,"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":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2303.00304","title":"Renderable Neural Radiance Map for Visual Navigation","created":"2023-03-01","cited_by_count":51,"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":"2403.12532","title":"UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All","created":"2024-03-19","cited_by_count":49,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2209.15266","title":"Data Poisoning Attacks Against Multimodal Encoders","created":"2022-09-30","cited_by_count":41,"area":"safety"},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2507.20939","title":"ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts","created":"2025-07-28","cited_by_count":41,"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":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2203.05796","title":"Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision","created":"2022-03-11","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":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","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":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33,"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":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2203.03897","title":"Geodesic Multi-Modal Mixup for Robust Fine-Tuning","created":"2022-03-08","cited_by_count":29,"area":null},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2306.09244","title":"Text Promptable Surgical Instrument Segmentation with Vision-Language Models","created":"2023-06-15","cited_by_count":28,"area":"mllm"},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","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":"2401.08045","title":"Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities","created":"2024-01-16","cited_by_count":24,"area":"driving"},{"id":"2112.01832","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","created":"2021-12-03","cited_by_count":23,"area":null},{"id":"2309.17093","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","created":"2023-09-29","cited_by_count":23,"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":"2405.16108","title":"OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2502.00848","title":"RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning","created":"2025-02-02","cited_by_count":20,"area":"rag"},{"id":"2204.03382","title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","created":"2022-04-07","cited_by_count":19,"area":null},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"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":"2303.06591","title":"Accommodating Audio Modality in CLIP for Multimodal Processing","created":"2023-03-12","cited_by_count":18,"area":"mllm"},{"id":"2406.18113","title":"Chrono: A Simple Blueprint for Representing Time in MLLMs","created":"2024-06-26","cited_by_count":18,"area":"mllm"},{"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":"2306.10159","title":"Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos","created":"2023-06-16","cited_by_count":17,"area":"mllm"},{"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":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2205.00132","title":"Learn to Understand Negation in Video Retrieval","created":"2022-04-30","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":"2302.07919","title":"COVID-VTS: Fact Extraction and Verification on Short Video Platforms","created":"2023-02-15","cited_by_count":15,"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":"2308.11551","title":"Multi-event Video-Text Retrieval","created":"2023-08-22","cited_by_count":15,"area":null},{"id":"2404.09011","title":"PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization","created":"2024-04-13","cited_by_count":15,"area":"mllm"},{"id":"2503.15949","title":"CausalCLIPSeg: Unlocking CLIP's Potential in Referring Medical Image Segmentation with Causal Intervention","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2202.13562","title":"Name Your Style: An Arbitrary Artist-aware Image Style Transfer","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2207.05333","title":"IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training","created":"2022-07-12","cited_by_count":14,"area":"mllm"},{"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":"2209.09502","title":"GAMA: Generative Adversarial Multi-Object Scene Attacks","created":"2022-09-20","cited_by_count":13,"area":null},{"id":"2306.10191","title":"Neural Priming for Sample-Efficient Adaptation","created":"2023-06-16","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}],"next_cursor":"100"}