{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"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":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"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":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123},{"id":"2404.03413","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","created":"2024-04-04","cited_by_count":118},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87},{"id":"1912.02379","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","created":"2019-12-05","cited_by_count":61},{"id":"2004.13278","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","created":"2020-04-28","cited_by_count":55},{"id":"1907.01166","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","created":"2019-07-02","cited_by_count":52},{"id":"2405.03133","title":"Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training","created":"2024-05-06","cited_by_count":37},{"id":"2010.10095","title":"BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues","created":"2020-10-20","cited_by_count":22},{"id":"2205.00423","title":"UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog","created":"2022-05-01","cited_by_count":19},{"id":"2212.05765","title":"Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue","created":"2022-12-12","cited_by_count":18},{"id":"2103.13361","title":"Structured Co-reference Graph Attention for Video-grounded Dialogue","created":"2021-03-24","cited_by_count":17},{"id":"2006.15319","title":"Video-Grounded Dialogues with Pretrained Generation Language Models","created":"2020-06-27","cited_by_count":16},{"id":"2110.06894","title":"Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning","created":"2021-10-13","cited_by_count":15},{"id":"2303.09713","title":"CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos","created":"2023-03-17","cited_by_count":14},{"id":"2109.08475","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","created":"2021-09-17","cited_by_count":13},{"id":"2001.06206","title":"Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System","created":"2020-01-17","cited_by_count":11},{"id":"2103.00820","title":"Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues","created":"2021-03-01","cited_by_count":11},{"id":"2207.03656","title":"Video Dialog as Conversation about Objects Living in Space-Time","created":"2022-07-08","cited_by_count":11},{"id":"2109.06013","title":"Learning to Ground Visual Objects for Visual Dialog","created":"2021-09-13","cited_by_count":10},{"id":"2205.14693","title":"VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution","created":"2022-05-29","cited_by_count":7},{"id":"2210.14512","title":"End-to-End Multimodal Representation Learning for Video Dialog","created":"2022-10-26","cited_by_count":5},{"id":"2211.13235","title":"Unified Multimodal Model with Unlikelihood Training for Visual Dialog","created":"2022-11-23","cited_by_count":5},{"id":"2310.16590","title":"$\\mathbb{VD}$-$\\mathbb{GR}$: Boosting $\\mathbb{V}$isual $\\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\\mathbb{GR}$aphs","created":"2023-10-25","cited_by_count":4},{"id":"2208.10353","title":"Neuro-Symbolic Visual Dialog","created":"2022-08-22","cited_by_count":3},{"id":"2402.13146","title":"OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog","created":"2024-02-20","cited_by_count":3},{"id":"2407.02218","title":"Multi-Modal Video Dialog State Tracking in the Wild","created":"2024-07-02","cited_by_count":3}],"next_cursor":null}