{"total":21,"rows":[{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2106.04128","title":"Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback","created":"2021-06-08","cited_by_count":29,"area":null},{"id":"2104.03015","title":"RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network","created":"2021-04-07","cited_by_count":27,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2105.12337","title":"What data do we need for training an AV motion planner?","created":"2021-05-26","cited_by_count":15,"area":null},{"id":"2306.16713","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2206.01923","title":"From Pixels to Objects: Cubic Visual Attention for Visual Question Answering","created":"2022-06-04","cited_by_count":7,"area":null},{"id":"2304.07747","title":"Language Guided Local Infiltration for Interactive Image Retrieval","created":"2023-04-16","cited_by_count":6,"area":null},{"id":"2103.04020","title":"NeRD: Neural Representation of Distribution for Medical Image Segmentation","created":"2021-03-06","cited_by_count":5,"area":null},{"id":"2204.11004","title":"Training and challenging models for text-guided fashion image retrieval","created":"2022-04-23","cited_by_count":5,"area":null},{"id":"2304.00719","title":"Multi-Modal Representation Learning with Text-Driven Soft Masks","created":"2023-04-03","cited_by_count":5,"area":null},{"id":"2103.06032","title":"Cross-modal Image Retrieval with Deep Mutual Information Maximization","created":"2021-03-10","cited_by_count":2,"area":null},{"id":"2305.03971","title":"Adaptive loose optimization for robust question answering","created":"2023-05-06","cited_by_count":2,"area":null},{"id":"2309.04734","title":"Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2203.01681","title":"Quantity over Quality: Training an AV Motion Planner with Large Scale Commodity Vision Data","created":"2022-03-03","cited_by_count":0,"area":null},{"id":"2212.00749","title":"Multimodal Query-guided Object Localization","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2302.09208","title":"Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2310.02528","title":"On the Cognition of Visual Question Answering Models and Human Intelligence: A Comparative Study","created":"2023-10-04","cited_by_count":0,"area":null}],"next_cursor":null}