{"total":316,"rows":[{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985,"area":null},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"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":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253,"area":null},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234,"area":null},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225,"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":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188,"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":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162,"area":null},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"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":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135,"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":"2507.04590","title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents","created":"2025-07-07","cited_by_count":116,"area":null},{"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":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95,"area":null},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93,"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":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"area":null},{"id":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83,"area":null},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2303.12112","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","created":"2023-03-21","cited_by_count":78,"area":null},{"id":"2203.07111","title":"Disentangled Representation Learning for Text-Video Retrieval","created":"2022-03-14","cited_by_count":77,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"area":null},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","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":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71,"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":"2206.08522","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","created":"2022-06-17","cited_by_count":68,"area":null},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2104.00332","title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training","created":"2021-04-01","cited_by_count":64,"area":null},{"id":"2408.02629","title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","created":"2024-08-05","cited_by_count":62,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"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":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53,"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":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2105.14462","title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","created":"2021-05-30","cited_by_count":44,"area":null},{"id":"2103.05284","title":"Open-book Video Captioning with Retrieve-Copy-Generate Network","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42,"area":null},{"id":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42,"area":null},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41,"area":null},{"id":"2410.00741","title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","created":"2024-10-01","cited_by_count":41,"area":null},{"id":"2506.12103","title":"The Amazon Nova Family of Models: Technical Report and Model Card","created":"2025-03-17","cited_by_count":41,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2111.08919","title":"EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching","created":"2021-11-17","cited_by_count":36,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","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":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2209.00465","title":"On Grounded Planning for Embodied Tasks with Language Models","created":"2022-08-29","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":"2211.12824","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","created":"2022-11-23","cited_by_count":32,"area":null},{"id":"2107.12059","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2305.03347","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","created":"2023-05-05","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":"2308.11606","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2206.00100","title":"VALHALLA: Visual Hallucination for Machine Translation","created":"2022-05-31","cited_by_count":27,"area":null},{"id":"2109.04275","title":"M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining","created":"2021-09-09","cited_by_count":26,"area":null},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2205.06126","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","created":"2022-05-12","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":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25,"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":"2405.04682","title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","created":"2024-05-07","cited_by_count":25,"area":null},{"id":"2104.09411","title":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training","created":"2021-04-19","cited_by_count":23,"area":null},{"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":"2305.17415","title":"Exploring Better Text Image Translation with Multimodal Codebook","created":"2023-05-27","cited_by_count":23,"area":null},{"id":"2410.01506","title":"Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2208.12526","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","created":"2022-08-26","cited_by_count":22,"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":"2309.12867","title":"Accurate and Fast Compressed Video Captioning","created":"2023-09-22","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","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":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","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}],"next_cursor":"100"}