{"list":"other","total":64,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"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":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"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":"2111.09734","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":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2303.00747","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","created":"2023-03-01","cited_by_count":326},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"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":"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":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"1911.01255","title":"pyannote.audio: neural building blocks for speaker diarization","created":"2019-11-04","cited_by_count":181},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"1907.13426","title":"Expectation-Maximization Attention Networks for Semantic Segmentation","created":"2019-07-31","cited_by_count":147},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116},{"id":"2003.07758","title":"Multi-modal Dense Video Captioning","created":"2020-03-17","cited_by_count":113},{"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":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2104.04045","title":"End-to-end speaker segmentation for overlap-aware resegmentation","created":"2021-04-08","cited_by_count":80},{"id":"2005.08271","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","created":"2020-05-17","cited_by_count":76},{"id":"1804.00100","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","created":"2018-03-31","cited_by_count":68},{"id":"1803.04376","title":"Discriminability objective for training descriptive captions","created":"2018-03-12","cited_by_count":67},{"id":"1804.08274","title":"Jointly Localizing and Describing Events for Dense Video Captioning","created":"2018-04-23","cited_by_count":60},{"id":"1904.03870","title":"Streamlined Dense Video Captioning","created":"2019-04-08","cited_by_count":57},{"id":"2211.11427","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","created":"2022-11-21","cited_by_count":57},{"id":"1710.02534","title":"Contrastive Learning for Image Captioning","created":"2017-10-06","cited_by_count":54},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50},{"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":"1909.09944","title":"Watch, Listen and Tell: Multi-modal Weakly Supervised Dense Event Captioning","created":"2019-09-22","cited_by_count":38},{"id":"1803.08314","title":"Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data","created":"2018-03-22","cited_by_count":37},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35},{"id":"1503.01070","title":"Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research","created":"2015-03-03","cited_by_count":33},{"id":"2007.06877","title":"Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets","created":"2020-07-14","cited_by_count":27},{"id":"2208.10128","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","created":"2022-08-22","cited_by_count":26},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23},{"id":"2010.03667","title":"Rescribe: Authoring and Automatically Editing Audio Descriptions","created":"2020-10-07","cited_by_count":21},{"id":"1704.01502","title":"Weakly Supervised Dense Video Captioning","created":"2017-04-05","cited_by_count":18},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16},{"id":"2405.00983","title":"LLM-AD: Large Language Model based Audio Description System","created":"2024-05-02","cited_by_count":15},{"id":"2403.12922","title":"Contextual AD Narration with Interleaved Multimodal Sequence","created":"2024-03-19","cited_by_count":14},{"id":"2108.09151","title":"Group-based Distinctive Image Captioning with Memory Attention","created":"2021-08-20","cited_by_count":13},{"id":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9},{"id":"2204.03938","title":"On Distinctive Image Captioning via Comparing and Reweighting","created":"2022-04-08","cited_by_count":7}],"next_cursor":null}