{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"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":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"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":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2010.02824","title":"Support-set bottlenecks for video-text representation learning","created":"2020-10-06","cited_by_count":170},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"1801.00054","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","created":"2017-12-29","cited_by_count":105},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2011.11760","title":"Multimodal Pretraining for Dense Video Captioning","created":"2020-11-10","cited_by_count":79},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77},{"id":"1812.01969","title":"Summarizing Videos with Attention","created":"2018-12-05","cited_by_count":69},{"id":"2101.10511","title":"Generic Event Boundary Detection: A Benchmark for Event Segmentation","created":"2021-01-26","cited_by_count":65},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","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":"1708.09545","title":"Video Summarization with Attention-Based Encoder-Decoder Networks","created":"2017-08-31","cited_by_count":63},{"id":"1903.11328","title":"Rethinking the Evaluation of Video Summaries","created":"2019-03-27","cited_by_count":62},{"id":"1804.08274","title":"Jointly Localizing and Describing Events for Dense Video Captioning","created":"2018-04-23","cited_by_count":60},{"id":"2312.10300","title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","created":"2023-12-16","cited_by_count":54},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53},{"id":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44},{"id":"1707.04960","title":"Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach","created":"2017-07-16","cited_by_count":42},{"id":"1906.07901","title":"Multimodal Abstractive Summarization for How2 Videos","created":"2019-06-19","cited_by_count":41},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39},{"id":"2208.06773","title":"TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency","created":"2022-08-14","cited_by_count":35},{"id":"2007.08809","title":"SumGraph: Video Summarization via Recursive Graph Modeling","created":"2020-07-17","cited_by_count":32},{"id":"2303.00040","title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training","created":"2023-02-28","cited_by_count":32},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29},{"id":"2104.11530","title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","created":"2021-04-23","cited_by_count":26},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","cited_by_count":26},{"id":"2305.01735","title":"DiffuSum: Generation Enhanced Extractive Summarization with Diffusion","created":"2023-05-02","cited_by_count":25},{"id":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21},{"id":"2306.09324","title":"Single-Stage Visual Query Localization in Egocentric Videos","created":"2023-06-15","cited_by_count":20},{"id":"2204.00486","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","created":"2022-04-01","cited_by_count":19},{"id":"2403.16276","title":"Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding","created":"2024-03-24","cited_by_count":18},{"id":"2009.08018","title":"Multi-modal Summarization for Video-containing Documents","created":"2020-09-17","cited_by_count":13},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12},{"id":"2209.12164","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","created":"2022-09-25","cited_by_count":10},{"id":"2006.01410","title":"Transforming Multi-Concept Attention into Video Summarization","created":"2020-06-02","cited_by_count":9},{"id":"2306.10354","title":"LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning","created":"2023-06-17","cited_by_count":9},{"id":"1812.00722","title":"SUSiNet: See, Understand and Summarize it","created":"2018-12-03","cited_by_count":8},{"id":"2010.13626","title":"Classification of Important Segments in Educational Videos using Multimodal Features","created":"2020-10-26","cited_by_count":4},{"id":"2207.01050","title":"Exploiting Context Information for Generic Event Boundary Captioning","created":"2022-07-03","cited_by_count":3}],"next_cursor":null}