{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2001.09099","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","created":"2020-01-24","cited_by_count":215},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"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":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"1906.07651","title":"Scheduled Sampling for Transformers","created":"2019-06-18","cited_by_count":48},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40},{"id":"2403.17998","title":"Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval","created":"2024-03-26","cited_by_count":33},{"id":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31},{"id":"2305.08953","title":"Motion Question Answering via Modular Motion Programs","created":"2023-05-15","cited_by_count":27},{"id":"2312.00360","title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","created":"2023-12-01","cited_by_count":25},{"id":"2105.08481","title":"Parallel Attention Network with Sequence Matching for Video Grounding","created":"2021-05-18","cited_by_count":22},{"id":"2202.01727","title":"Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks","created":"2022-02-03","cited_by_count":20},{"id":"2004.09144","title":"Transformer Reasoning Network for Image-Text Matching and Retrieval","created":"2020-04-20","cited_by_count":19},{"id":"2212.07592","title":"Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration","created":"2022-12-15","cited_by_count":11},{"id":"2305.04195","title":"Cross-Modal Retrieval for Motion and Text via DropTriple Loss","created":"2023-05-07","cited_by_count":11},{"id":"2305.15842","title":"Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language","created":"2023-05-25","cited_by_count":11},{"id":"2205.05854","title":"Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos","created":"2022-05-12","cited_by_count":10},{"id":"2203.10719","title":"LocATe: End-to-end Localization of Actions in 3D with Transformers","created":"2022-03-21","cited_by_count":8},{"id":"2305.18969","title":"MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction","created":"2023-05-30","cited_by_count":8},{"id":"2210.15187","title":"Learning Joint Representation of Human Motion and Language","created":"2022-10-27","cited_by_count":3}],"next_cursor":null}