{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"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":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"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":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"1812.00087","title":"MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment","created":"2018-11-30","cited_by_count":145},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"1901.06829","title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos","created":"2019-01-21","cited_by_count":60},{"id":"2012.08508","title":"Attention over learned object embeddings enables complex visual reasoning","created":"2020-12-15","cited_by_count":59},{"id":"2209.13306","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","created":"2022-09-27","cited_by_count":42},{"id":"1801.01582","title":"Object Referring in Videos with Language and Human Gaze","created":"2018-01-04","cited_by_count":40},{"id":"2003.10469","title":"Learning Object Permanence from Video","created":"2020-03-23","cited_by_count":30},{"id":"2103.14232","title":"ACRE: Abstract Causal REasoning Beyond Covariation","created":"2021-03-26","cited_by_count":30},{"id":"2111.12990","title":"Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning","created":"2021-11-25","cited_by_count":27},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24},{"id":"2011.00966","title":"Diverse Image Captioning with Context-Object Split Latent Spaces","created":"2020-11-02","cited_by_count":22},{"id":"2110.00519","title":"Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images","created":"2021-10-01","cited_by_count":14},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12},{"id":"2203.05928","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","created":"2022-03-11","cited_by_count":12},{"id":"1808.04446","title":"Visual Reasoning with Multi-hop Feature Modulation","created":"2018-08-03","cited_by_count":7},{"id":"1809.01943","title":"Cascaded Mutual Modulation for Visual Reasoning","created":"2018-09-06","cited_by_count":5}],"next_cursor":null}