{"list":"other","total":53,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"1612.06321","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","created":"2016-12-19","cited_by_count":238},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"1511.05879","title":"Particular object retrieval with integral max-pooling of CNN activations","created":"2015-11-18","cited_by_count":161},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"1604.01325","title":"Deep Image Retrieval: Learning global representations for image search","created":"2016-04-05","cited_by_count":147},{"id":"2103.09382","title":"SPICE: Semantic Pseudo-labeling for Image Clustering","created":"2021-03-17","cited_by_count":104},{"id":"2307.00524","title":"Large Language Models Enable Few-Shot Clustering","created":"2023-07-02","cited_by_count":72},{"id":"2104.01429","title":"Graph Contrastive Clustering","created":"2021-04-03","cited_by_count":61},{"id":"2210.11680","title":"Twin Contrastive Learning for Online Clustering","created":"2022-10-21","cited_by_count":60},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58},{"id":"2309.04269","title":"From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting","created":"2023-09-08","cited_by_count":52},{"id":"2012.11150","title":"Improving Unsupervised Image Clustering With Robust Learning","created":"2020-12-21","cited_by_count":51},{"id":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44},{"id":"1804.05312","title":"Local Descriptors Optimized for Average Precision","created":"2018-04-15","cited_by_count":43},{"id":"2106.01908","title":"You Never Cluster Alone","created":"2021-06-03","cited_by_count":38},{"id":"1905.06358","title":"Local Features and Visual Words Emerge in Activations","created":"2019-05-15","cited_by_count":37},{"id":"2310.11989","title":"Image Clustering with External Guidance","created":"2023-10-18","cited_by_count":36},{"id":"2208.09849","title":"Semantic-Enhanced Image Clustering","created":"2022-08-21","cited_by_count":25},{"id":"2304.01042","title":"DivClust: Controlling Diversity in Deep Clustering","created":"2023-04-03","cited_by_count":18},{"id":"2209.12396","title":"Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric","created":"2022-09-26","cited_by_count":17},{"id":"2106.16209","title":"A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering","created":"2021-06-30","cited_by_count":9},{"id":"2304.13995","title":"Rotation and Translation Invariant Representation Learning with Implicit Neural Representations","created":"2023-04-27","cited_by_count":4},{"id":"1903.10092","title":"An Exact No Free Lunch Theorem for Community Detection","created":"2019-03-25","cited_by_count":2}],"next_cursor":null}