{"list":"other","total":54,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"1611.09571","title":"Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model","created":"2016-11-29","cited_by_count":91},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"1809.02805","title":"Faithful Multimodal Explanation for Visual Question Answering","created":"2018-09-08","cited_by_count":64},{"id":"1905.09998","title":"Self-Critical Reasoning for Robust Visual Question Answering","created":"2019-05-24","cited_by_count":61},{"id":"1610.01563","title":"DeepGaze II: Reading fixations from deep features trained on object recognition","created":"2016-10-05","cited_by_count":55},{"id":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"2005.14310","title":"Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning","created":"2020-05-28","cited_by_count":53},{"id":"1805.01047","title":"EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction","created":"2018-05-02","cited_by_count":51},{"id":"1803.07464","title":"VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions","created":"2018-03-20","cited_by_count":50},{"id":"2010.07526","title":"Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs","created":"2020-10-15","cited_by_count":46},{"id":"2303.15274","title":"Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention","created":"2023-03-27","cited_by_count":38},{"id":"1806.09809","title":"Generating Counterfactual Explanations with Natural Language","created":"2018-06-26","cited_by_count":37},{"id":"1809.00567","title":"PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks","created":"2018-09-03","cited_by_count":32},{"id":"1909.02201","title":"Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach","created":"2019-09-05","cited_by_count":30},{"id":"2008.02912","title":"Predicting Visual Importance Across Graphic Design Types","created":"2020-08-07","cited_by_count":30},{"id":"1707.03123","title":"SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes","created":"2017-07-11","cited_by_count":29},{"id":"2007.14419","title":"AiR: Attention with Reasoning Capability","created":"2020-07-28","cited_by_count":28},{"id":"2301.02315","title":"TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction","created":"2023-01-05","cited_by_count":25},{"id":"2101.03392","title":"Generate Natural Language Explanations for Recommendation","created":"2021-01-09","cited_by_count":23},{"id":"2109.13701","title":"CIDEr-R: Robust Consensus-based Image Description Evaluation","created":"2021-09-28","cited_by_count":22},{"id":"2207.01166","title":"Target-absent Human Attention","created":"2022-07-04","cited_by_count":20},{"id":"2010.12852","title":"Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions","created":"2020-10-24","cited_by_count":19},{"id":"1704.07434","title":"Paying Attention to Descriptions Generated by Image Captioning Models","created":"2017-04-24","cited_by_count":12},{"id":"2203.06107","title":"REX: Reasoning-aware and Grounded Explanation","created":"2022-03-11","cited_by_count":12},{"id":"2404.12235","title":"Beyond Average: Individualized Visual Scanpath Prediction","created":"2024-04-18","cited_by_count":12},{"id":"2207.03133","title":"Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions","created":"2022-07-07","cited_by_count":6},{"id":"2006.11035","title":"Wave Propagation of Visual Stimuli in Focus of Attention","created":"2020-06-19","cited_by_count":3},{"id":"2407.02439","title":"Predicting Visual Attention in Graphic Design Documents","created":"2024-07-02","cited_by_count":3}],"next_cursor":null}