{"list":"other","total":62,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2003.08505","title":"A Metric Learning Reality Check","created":"2020-03-18","cited_by_count":321},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"1909.02701","title":"Visual Semantic Reasoning for Image-Text Matching","created":"2019-09-06","cited_by_count":185},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"1807.08024","title":"Explaining Image Classifiers by Counterfactual Generation","created":"2018-07-20","cited_by_count":144},{"id":"1511.06078","title":"Learning Deep Structure-Preserving Image-Text Embeddings","created":"2015-11-19","cited_by_count":139},{"id":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117},{"id":"1909.05506","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","created":"2019-09-12","cited_by_count":110},{"id":"1912.07538","title":"Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing","created":"2019-12-16","cited_by_count":108},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104},{"id":"2204.14095","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","created":"2022-04-29","cited_by_count":104},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"1406.5679","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","created":"2014-06-22","cited_by_count":99},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90},{"id":"1906.04402","title":"Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval","created":"2019-06-11","cited_by_count":83},{"id":"1804.01452","title":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input","created":"2018-04-04","cited_by_count":81},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72},{"id":"2112.09418","title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","created":"2021-12-17","cited_by_count":61},{"id":"1805.00833","title":"Learnable PINs: Cross-Modal Embeddings for Person Identity","created":"2018-05-02","cited_by_count":60},{"id":"1709.01362","title":"Predicting Visual Features from Text for Image and Video Caption Retrieval","created":"2017-09-05","cited_by_count":53},{"id":"2105.02192","title":"Audio Retrieval with Natural Language Queries","created":"2021-05-05","cited_by_count":49},{"id":"2008.06884","title":"DeVLBert: Learning Deconfounded Visio-Linguistic Representations","created":"2020-08-16","cited_by_count":42},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37},{"id":"1804.01720","title":"Finding beans in burgers: Deep semantic-visual embedding with localization","created":"2018-04-05","cited_by_count":28},{"id":"2003.03669","title":"Adaptive Offline Quintuplet Loss for Image-Text Matching","created":"2020-03-07","cited_by_count":26},{"id":"2111.01300","title":"Masking Modalities for Cross-modal Video Retrieval","created":"2021-11-01","cited_by_count":23},{"id":"2007.08617","title":"Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval","created":"2020-07-16","cited_by_count":20},{"id":"1608.07973","title":"Linking Image and Text with 2-Way Nets","created":"2016-08-29","cited_by_count":14},{"id":"2203.13645","title":"Audio-text Retrieval in Context","created":"2022-03-25","cited_by_count":10}],"next_cursor":null}