{"list":"other","total":64,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82},{"id":"2005.05402","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","created":"2020-05-11","cited_by_count":79},{"id":"2009.07602","title":"UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation","created":"2020-09-16","cited_by_count":60},{"id":"2403.14599","title":"MyVLM: Personalizing VLMs for User-Specific Queries","created":"2024-03-21","cited_by_count":58},{"id":"1611.04021","title":"Leveraging Video Descriptions to Learn Video Question Answering","created":"2016-11-12","cited_by_count":55},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46},{"id":"2212.08158","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","created":"2022-12-15","cited_by_count":43},{"id":"1906.04375","title":"Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning","created":"2019-06-11","cited_by_count":42},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35},{"id":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34},{"id":"2406.09175","title":"ReMI: A Dataset for Reasoning with Multiple Images","created":"2024-06-13","cited_by_count":30},{"id":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28},{"id":"1912.01496","title":"Knowledge-Enriched Visual Storytelling","created":"2019-12-03","cited_by_count":26},{"id":"2008.11976","title":"Visual Question Answering on Image Sets","created":"2020-08-27","cited_by_count":26},{"id":"1805.10973","title":"GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation","created":"2018-05-28","cited_by_count":23},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23},{"id":"2102.02963","title":"Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling","created":"2021-02-05","cited_by_count":22},{"id":"2309.16283","title":"Self-supervised Cross-view Representation Reconstruction for Change Captioning","created":"2023-09-28","cited_by_count":20},{"id":"2405.14040","title":"Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline","created":"2024-05-22","cited_by_count":19},{"id":"2311.09675","title":"Where Do People Tell Stories Online? Story Detection Across Online Communities","created":"2023-11-16","cited_by_count":17},{"id":"1806.06371","title":"Multimodal Grounding for Language Processing","created":"2018-06-17","cited_by_count":14},{"id":"2405.20810","title":"Context-aware Difference Distilling for Multi-change Captioning","created":"2024-05-31","cited_by_count":10},{"id":"2410.00324","title":"Vision Language Models See What You Want but not What You See","created":"2024-10-01","cited_by_count":10},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9},{"id":"2406.13763","title":"Through the Theory of Mind's Eye: Reading Minds with Multimodal Video Large Language Models","created":"2024-06-19","cited_by_count":9},{"id":"2310.17770","title":"GROOViST: A Metric for Grounding Objects in Visual Storytelling","created":"2023-10-26","cited_by_count":8},{"id":"2205.03774","title":"RoViST:Learning Robust Metrics for Visual Storytelling","created":"2022-05-08","cited_by_count":7},{"id":"2407.04559","title":"Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition","created":"2024-07-05","cited_by_count":5},{"id":"2304.14986","title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors","created":"2023-04-28","cited_by_count":2}],"next_cursor":null}