{"list":"other","total":123,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177},{"id":"1903.05854","title":"MirrorGAN: Learning Text-to-image Generation by Redescription","created":"2019-03-14","cited_by_count":176},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2001.07416","title":"Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities","created":"2020-01-21","cited_by_count":126},{"id":"2104.12836","title":"Multimodal Contrastive Training for Visual Representation Learning","created":"2021-04-26","cited_by_count":124},{"id":"2305.15525","title":"Large Language Models are Few-Shot Health Learners","created":"2023-05-24","cited_by_count":118},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2205.14204","title":"Multimodal Masked Autoencoders Learn Transferable Representations","created":"2022-05-27","cited_by_count":109},{"id":"1903.03295","title":"Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos","created":"2019-03-08","cited_by_count":104},{"id":"1907.11879","title":"Multi-task Self-Supervised Learning for Human Activity Detection","created":"2019-07-27","cited_by_count":102},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98},{"id":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94},{"id":"2402.11838","title":"UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction","created":"2024-02-19","cited_by_count":87},{"id":"1611.01942","title":"DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing","created":"2016-11-07","cited_by_count":84},{"id":"1903.06496","title":"MFAS: Multimodal Fusion Architecture Search","created":"2019-03-15","cited_by_count":84},{"id":"1806.07110","title":"Modality Distillation with Multiple Stream Networks for Action Recognition","created":"2018-06-19","cited_by_count":83},{"id":"2206.02909","title":"Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data","created":"2022-06-06","cited_by_count":75},{"id":"2310.09605","title":"Penetrative AI: Making LLMs Comprehend the Physical World","created":"2023-10-14","cited_by_count":64},{"id":"2303.12311","title":"Frozen Language Model Helps ECG Zero-Shot Learning","created":"2023-03-22","cited_by_count":62},{"id":"2204.04588","title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","created":"2022-04-10","cited_by_count":55},{"id":"2111.00418","title":"Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances","created":"2021-10-31","cited_by_count":54},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53},{"id":"2305.01836","title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation","created":"2023-05-03","cited_by_count":53},{"id":"2402.10350","title":"Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review","created":"2024-02-15","cited_by_count":53},{"id":"1910.02212","title":"Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction","created":"2019-10-05","cited_by_count":50},{"id":"1910.04641","title":"Cross-modal knowledge distillation for action recognition","created":"2019-10-10","cited_by_count":45},{"id":"2202.02691","title":"TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network","created":"2022-02-06","cited_by_count":41},{"id":"2206.13508","title":"Data Augmentation techniques in time series domain: A survey and taxonomy","created":"2022-06-25","cited_by_count":41},{"id":"1801.00820","title":"Stratified Transfer Learning for Cross-domain Activity Recognition","created":"2017-12-25","cited_by_count":40},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38},{"id":"2009.00210","title":"Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition","created":"2020-09-01","cited_by_count":37},{"id":"2210.14395","title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","created":"2022-10-26","cited_by_count":37},{"id":"2004.12070","title":"Deep Multimodal Neural Architecture Search","created":"2020-04-25","cited_by_count":34},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31},{"id":"1912.10982","title":"DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition","created":"2019-12-23","cited_by_count":30},{"id":"2102.02340","title":"MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records","created":"2021-02-03","cited_by_count":30},{"id":"2108.00702","title":"Improving Deep Learning for HAR with shallow LSTMs","created":"2021-08-02","cited_by_count":30},{"id":"2206.06629","title":"Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition","created":"2022-06-14","cited_by_count":29},{"id":"2310.04942","title":"Large Language Models for Spatial Trajectory Patterns Mining","created":"2023-10-07","cited_by_count":27},{"id":"1807.07963","title":"Deep Transfer Learning for Cross-domain Activity Recognition","created":"2018-07-20","cited_by_count":25},{"id":"2112.01849","title":"Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition","created":"2021-10-08","cited_by_count":25},{"id":"2401.02416","title":"ODIN: A Single Model for 2D and 3D Segmentation","created":"2024-01-04","cited_by_count":25},{"id":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23},{"id":"2401.09093","title":"RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks","created":"2024-01-17","cited_by_count":22},{"id":"2402.01049","title":"IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition","created":"2024-02-01","cited_by_count":22},{"id":"2102.03353","title":"Cross-domain Activity Recognition via Substructural Optimal Transport","created":"2021-01-29","cited_by_count":21},{"id":"2107.11508","title":"Imbalanced Big Data Oversampling: Taxonomy, Algorithms, Software, Guidelines and Future Directions","created":"2021-07-24","cited_by_count":21},{"id":"2308.04369","title":"SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition","created":"2023-08-08","cited_by_count":20},{"id":"2305.03187","title":"Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition","created":"2023-05-04","cited_by_count":19},{"id":"1803.10299","title":"Multi-Modal Data Augmentation for End-to-End ASR","created":"2018-03-27","cited_by_count":18},{"id":"2212.14453","title":"Learning Multimodal Data Augmentation in Feature Space","created":"2022-12-29","cited_by_count":18},{"id":"2005.05085","title":"Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices","created":"2020-05-07","cited_by_count":17},{"id":"2201.02849","title":"Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition","created":"2022-01-08","cited_by_count":17},{"id":"2107.06252","title":"Dance2Music: Automatic Dance-driven Music Generation","created":"2021-07-13","cited_by_count":16},{"id":"2006.14435","title":"DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors","created":"2020-06-25","cited_by_count":14},{"id":"2401.10185","title":"Transfer Learning in Human Activity Recognition: A Survey","created":"2024-01-18","cited_by_count":14},{"id":"1810.08691","title":"Audio-Based Activities of Daily Living (ADL) Recognition with Large-Scale Acoustic Embeddings from Online Videos","created":"2018-10-19","cited_by_count":13}],"next_cursor":"100"}