{"list":"other","total":73,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1904.03189","title":"Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?","created":"2019-04-05","cited_by_count":675},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2102.02766","title":"Designing an Encoder for StyleGAN Image Manipulation","created":"2021-02-04","cited_by_count":544},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2106.05744","title":"Pivotal Tuning for Latent-based Editing of Real Images","created":"2021-06-10","cited_by_count":427},{"id":"2005.09635","title":"InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs","created":"2020-05-18","cited_by_count":394},{"id":"2003.03808","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","created":"2020-03-08","cited_by_count":358},{"id":"2008.02401","title":"StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows","created":"2020-08-06","cited_by_count":349},{"id":"1703.04394","title":"Zero-Shot Learning -- The Good, the Bad and the Ugly","created":"2017-03-13","cited_by_count":255},{"id":"2004.10956","title":"Few-Shot Class-Incremental Learning","created":"2020-04-23","cited_by_count":251},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"2111.15666","title":"HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing","created":"2021-11-30","cited_by_count":208},{"id":"2003.04390","title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","created":"2020-03-09","cited_by_count":179},{"id":"1503.08677","title":"Label-Embedding for Image Classification","created":"2015-03-30","cited_by_count":165},{"id":"2102.06583","title":"Reviving Iterative Training with Mask Guidance for Interactive Segmentation","created":"2021-02-12","cited_by_count":163},{"id":"1901.07973","title":"DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images","created":"2019-01-23","cited_by_count":134},{"id":"2103.04059","title":"Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning","created":"2021-03-06","cited_by_count":115},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"id":"2112.00719","title":"HyperInverter: Improving StyleGAN Inversion via Hypernetwork","created":"2021-12-01","cited_by_count":85},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72},{"id":"2201.08361","title":"Stitch it in Time: GAN-Based Facial Editing of Real Videos","created":"2022-01-20","cited_by_count":68},{"id":"2006.11149","title":"Compositional Learning of Image-Text Query for Image Retrieval","created":"2020-06-19","cited_by_count":57},{"id":"2009.01719","title":"Grounded Language Learning Fast and Slow","created":"2020-09-03","cited_by_count":54},{"id":"1810.10665","title":"Engaging Image Captioning Via Personality","created":"2018-10-25","cited_by_count":51},{"id":"2111.14745","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","created":"2021-11-29","cited_by_count":49},{"id":"1511.05284","title":"Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data","created":"2015-11-17","cited_by_count":36},{"id":"1704.06485","title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","created":"2017-04-21","cited_by_count":35},{"id":"1810.00846","title":"Classification from Positive, Unlabeled and Biased Negative Data","created":"2018-10-01","cited_by_count":34},{"id":"2007.06271","title":"RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning","created":"2020-07-13","cited_by_count":32},{"id":"1606.07770","title":"Captioning Images with Diverse Objects","created":"2016-06-24","cited_by_count":27},{"id":"2112.03185","title":"Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples","created":"2021-12-06","cited_by_count":24},{"id":"1904.08034","title":"People infer recursive visual concepts from just a few examples","created":"2019-04-17","cited_by_count":23},{"id":"2007.04546","title":"Wandering Within a World: Online Contextualized Few-Shot Learning","created":"2020-07-09","cited_by_count":22},{"id":"2010.03276","title":"ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization","created":"2020-10-07","cited_by_count":22},{"id":"1811.07662","title":"Intention Oriented Image Captions with Guiding Objects","created":"2018-11-19","cited_by_count":20},{"id":"1804.03803","title":"Decoupled Novel Object Captioner","created":"2018-04-11","cited_by_count":15},{"id":"1608.07639","title":"Learning to generalize to new compositions in image understanding","created":"2016-08-27","cited_by_count":12},{"id":"2107.01518","title":"Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans","created":"2021-07-04","cited_by_count":12},{"id":"2111.07993","title":"CoLLIE: Continual Learning of Language Grounding from Language-Image Embeddings","created":"2021-11-15","cited_by_count":11},{"id":"2107.13978","title":"Personalized Image Semantic Segmentation","created":"2021-07-24","cited_by_count":9},{"id":"2001.10642","title":"Binary Classification from Positive Data with Skewed Confidence","created":"2020-01-29","cited_by_count":8},{"id":"2202.04670","title":"Can Humans Do Less-Than-One-Shot Learning?","created":"2022-02-09","cited_by_count":7},{"id":"1806.02664","title":"Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning","created":"2018-06-07","cited_by_count":6},{"id":"1908.00047","title":"Image Captioning with Unseen Objects","created":"2019-07-31","cited_by_count":6},{"id":"2106.01499","title":"Personalizing Pre-trained Models","created":"2021-06-02","cited_by_count":5}],"next_cursor":null}