{"total":20,"rows":[{"id":"2104.09829","title":"Detector-Free Weakly Supervised Grounding by Separation","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2407.18589","title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation","created":"2024-07-26","cited_by_count":12,"area":null},{"id":"2205.04908","title":"Shadow-Aware Dynamic Convolution for Shadow Removal","created":"2022-05-10","cited_by_count":11,"area":null},{"id":"2408.01723","title":"A Novel Evaluation Framework for Image2Text Generation","created":"2024-08-03","cited_by_count":11,"area":null},{"id":"2109.05797","title":"Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2201.01984","title":"Image Captioning via Compact Bidirectional Architecture","created":"2022-01-06","cited_by_count":7,"area":null},{"id":"2209.02574","title":"Cross Modal Compression: Towards Human-comprehensible Semantic Compression","created":"2022-09-06","cited_by_count":7,"area":null},{"id":"2108.11875","title":"A spatio-temporal LSTM model to forecast across multiple temporal and spatial scales","created":"2021-08-26","cited_by_count":6,"area":null},{"id":"2207.10897","title":"Efficient Modeling of Future Context for Image Captioning","created":"2022-07-22","cited_by_count":5,"area":null},{"id":"2211.09460","title":"Progressive Tree-Structured Prototype Network for End-to-End Image Captioning","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2202.11811","title":"NeuroView-RNN: It's About Time","created":"2022-02-23","cited_by_count":2,"area":null},{"id":"2109.11398","title":"Scene Graph Generation for Better Image Captioning?","created":"2021-09-23","cited_by_count":1,"area":null},{"id":"2509.12534","title":"DeepEyeNet: Generating Medical Report for Retinal Images","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2201.08830","title":"APack: Off-Chip, Lossless Data Compression for Efficient Deep Learning Inference","created":"2022-01-21","cited_by_count":0,"area":null},{"id":"2207.05682","title":"Long Short-Term Memory to predict 3D Amino acids Positions in GPCR Molecular Dynamics","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2307.07370","title":"AIC-AB NET: A Neural Network for Image Captioning with Spatial Attention and Text Attributes","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2402.15923","title":"Predicting Outcomes in Video Games with Long Short Term Memory Networks","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2409.00731","title":"A Critical Analysis on Machine Learning Techniques for Video-based Human Activity Recognition of Surveillance Systems: A Review","created":"2024-09-01","cited_by_count":0,"area":null},{"id":"2602.13352","title":"Using Deep Learning to Generate Semantically Correct Hindi Captions","created":"2026-02-13","cited_by_count":0,"area":null}],"next_cursor":null}