{"list":"other","total":76,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"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":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","created":"2020-02-15","cited_by_count":259},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"1903.05987","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","created":"2019-03-14","cited_by_count":167},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"1904.04357","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","created":"2019-04-08","cited_by_count":146},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"1803.10906","title":"Motion-Appearance Co-Memory Networks for Video Question Answering","created":"2018-03-29","cited_by_count":95},{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84},{"id":"2008.09105","title":"Location-aware Graph Convolutional Networks for Video Question Answering","created":"2020-08-07","cited_by_count":80},{"id":"1707.00836","title":"DeepStory: Video Story QA by Deep Embedded Memory Networks","created":"2017-07-04","cited_by_count":68},{"id":"2104.14085","title":"Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering","created":"2021-04-29","cited_by_count":56},{"id":"1910.10706","title":"KnowIT VQA: Answering Knowledge-Based Questions about Videos","created":"2019-10-23","cited_by_count":53},{"id":"2012.05710","title":"Look Before you Speak: Visually Contextualized Utterances","created":"2020-12-10","cited_by_count":53},{"id":"2005.03356","title":"DramaQA: Character-Centered Video Story Understanding with Hierarchical QA","created":"2020-05-07","cited_by_count":45},{"id":"2109.05125","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","created":"2021-09-10","cited_by_count":44},{"id":"1612.01669","title":"MarioQA: Answering Questions by Watching Gameplay Videos","created":"2016-12-06","cited_by_count":42},{"id":"2112.02399","title":"VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts","created":"2021-12-04","cited_by_count":42},{"id":"1707.06355","title":"Video Question Answering via Attribute-Augmented Attention Network Learning","created":"2017-07-20","cited_by_count":39},{"id":"2007.02036","title":"Modality Shifting Attention Network for Multi-modal Video Question Answering","created":"2020-07-04","cited_by_count":38},{"id":"1910.00216","title":"Revisiting Fine-tuning for Few-shot Learning","created":"2019-10-01","cited_by_count":29},{"id":"2009.08043","title":"Self-supervised pre-training and contrastive representation learning for multiple-choice video QA","created":"2020-09-17","cited_by_count":28},{"id":"2104.09411","title":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training","created":"2021-04-19","cited_by_count":23},{"id":"1912.01046","title":"TutorialVQA: Question Answering Dataset for Tutorial Videos","created":"2019-12-02","cited_by_count":20},{"id":"2011.07735","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","created":"2020-11-16","cited_by_count":20},{"id":"2005.06409","title":"Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA","created":"2020-05-13","cited_by_count":13},{"id":"2104.03762","title":"Video Question Answering with Phrases via Semantic Roles","created":"2021-04-08","cited_by_count":13},{"id":"2104.05166","title":"Object-Centric Representation Learning for Video Question Answering","created":"2021-04-12","cited_by_count":7},{"id":"1909.02218","title":"A Better Way to Attend: Attention with Trees for Video Question Answering","created":"2019-09-05","cited_by_count":6}],"next_cursor":null}