{"list":"other","total":58,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"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":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"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":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"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":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"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":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"id":"2011.13367","title":"SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos","created":"2020-11-26","cited_by_count":131},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80},{"id":"2211.03679","title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","created":"2022-11-07","cited_by_count":64},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57},{"id":"1912.01326","title":"A Context-Aware Loss Function for Action Spotting in Soccer Videos","created":"2019-12-03","cited_by_count":56},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52},{"id":"2104.09333","title":"Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting","created":"2021-04-19","cited_by_count":43},{"id":"2401.01505","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","created":"2024-01-03","cited_by_count":41},{"id":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40},{"id":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","cited_by_count":38},{"id":"2208.08190","title":"DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations","created":"2022-08-17","cited_by_count":37},{"id":"2210.02365","title":"SoccerNet 2022 Challenges Results","created":"2022-10-05","cited_by_count":28},{"id":"2205.10450","title":"Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors","created":"2022-05-20","cited_by_count":27},{"id":"2204.06859","title":"Semi-Supervised Training to Improve Player and Ball Detection in Soccer","created":"2022-04-14","cited_by_count":25},{"id":"2004.07209","title":"Using Player's Body-Orientation to Model Pass Feasibility in Soccer","created":"2020-04-15","cited_by_count":20},{"id":"2309.06006","title":"SoccerNet 2023 Challenges Results","created":"2023-09-12","cited_by_count":20},{"id":"2204.04049","title":"Efficient tracking of team sport players with few game-specific annotations","created":"2022-04-08","cited_by_count":17},{"id":"2309.01270","title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","created":"2023-09-03","cited_by_count":17},{"id":"2206.07846","title":"Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022","created":"2022-06-15","cited_by_count":14},{"id":"2304.04220","title":"Towards Active Learning for Action Spotting in Association Football Videos","created":"2023-04-09","cited_by_count":14},{"id":"2401.09942","title":"Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking","created":"2024-01-18","cited_by_count":13},{"id":"2304.02939","title":"All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes","created":"2023-04-06","cited_by_count":8},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7},{"id":"2309.12067","title":"Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives","created":"2023-09-21","cited_by_count":7},{"id":"2402.09650","title":"Foul prediction with estimated poses from soccer broadcast video","created":"2024-02-15","cited_by_count":7},{"id":"2202.01031","title":"MMSys'22 Grand Challenge on AI-based Video Production for Soccer","created":"2022-02-02","cited_by_count":6},{"id":"2402.00163","title":"Improving Object Detection Quality in Football Through Super-Resolution Techniques","created":"2024-01-31","cited_by_count":6}],"next_cursor":null}