{"list":"other","total":61,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"1810.07212","title":"Cross-Modal and Hierarchical Modeling of Video and Text","created":"2018-10-16","cited_by_count":103},{"id":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99},{"id":"2212.04500","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","created":"2022-12-08","cited_by_count":90},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"1912.01601","title":"LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition","created":"2019-12-03","cited_by_count":65},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45},{"id":"2106.09212","title":"Long-Short Temporal Contrastive Learning of Video Transformers","created":"2021-06-17","cited_by_count":42},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37},{"id":"2311.16511","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","created":"2023-11-25","cited_by_count":36},{"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},{"id":"2201.05307","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","created":"2022-01-14","cited_by_count":30},{"id":"2405.07798","title":"FreeVA: Offline MLLM as Training-Free Video Assistant","created":"2024-05-13","cited_by_count":29},{"id":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19},{"id":"2204.03017","title":"Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency","created":"2022-04-06","cited_by_count":15},{"id":"2211.10636","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","created":"2022-11-19","cited_by_count":15},{"id":"2311.01233","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","created":"2023-11-02","cited_by_count":7}],"next_cursor":null}