{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151},{"id":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146},{"id":"1806.11146","title":"Adversarial Reprogramming of Neural Networks","created":"2018-06-28","cited_by_count":116},{"id":"2001.08702","title":"Lipreading using Temporal Convolutional Networks","created":"2020-01-23","cited_by_count":102},{"id":"2210.04831","title":"Visual Prompt Tuning for Test-time Domain Adaptation","created":"2022-10-10","cited_by_count":97},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95},{"id":"1911.12747","title":"ASR is all you need: cross-modal distillation for lip reading","created":"2019-11-28","cited_by_count":88},{"id":"1611.01599","title":"LipNet: End-to-End Sentence-level Lipreading","created":"2016-11-05","cited_by_count":80},{"id":"1802.06424","title":"End-to-end Audiovisual Speech Recognition","created":"2018-02-18","cited_by_count":73},{"id":"1703.04105","title":"Combining Residual Networks with LSTMs for Lipreading","created":"2017-03-12","cited_by_count":68},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63},{"id":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50},{"id":"2007.06504","title":"Towards Practical Lipreading with Distilled and Efficient Models","created":"2020-07-13","cited_by_count":45},{"id":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","cited_by_count":44},{"id":"1911.11502","title":"Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers","created":"2019-11-26","cited_by_count":41},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41},{"id":"2204.01725","title":"Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading","created":"2022-04-04","cited_by_count":39},{"id":"2102.07325","title":"Cross-modal Adversarial Reprogramming","created":"2021-02-15","cited_by_count":34},{"id":"2207.06020","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","created":"2022-07-13","cited_by_count":24},{"id":"1804.00732","title":"Speaker-Invariant Training via Adversarial Learning","created":"2018-04-02","cited_by_count":23},{"id":"1905.02540","title":"Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading","created":"2019-05-04","cited_by_count":22},{"id":"2003.05709","title":"Deformation Flow Based Two-Stream Network for Lip Reading","created":"2020-03-12","cited_by_count":22},{"id":"1703.10667","title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","created":"2017-03-30","cited_by_count":18},{"id":"2204.01265","title":"Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video","created":"2022-04-04","cited_by_count":18},{"id":"2208.04498","title":"Speaker-adaptive Lip Reading with User-dependent Padding","created":"2022-08-09","cited_by_count":17},{"id":"2108.11673","title":"Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference","created":"2021-08-26","cited_by_count":13},{"id":"2204.13004","title":"Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame","created":"2022-04-27","cited_by_count":9},{"id":"1906.02182","title":"Two-Stream Region Convolutional 3D Network for Temporal Activity Detection","created":"2019-06-05","cited_by_count":8},{"id":"1910.10605","title":"Speaker Adaptive Training using Model Agnostic Meta-Learning","created":"2019-10-23","cited_by_count":8},{"id":"2201.02692","title":"Improved Input Reprogramming for GAN Conditioning","created":"2022-01-07","cited_by_count":7}],"next_cursor":null}