{"total":20,"rows":[{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2301.00896","title":"Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos","created":"2023-01-03","cited_by_count":20,"area":null},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2102.00109","title":"SCAN: A Spatial Context Attentive Network for Joint Multi-Agent Intent Prediction","created":"2021-01-29","cited_by_count":9,"area":null},{"id":"2103.11313","title":"PGT: A Progressive Method for Training Models on Long Videos","created":"2021-03-21","cited_by_count":7,"area":null},{"id":"2109.04021","title":"Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours from Multimodal Videos","created":"2021-09-09","cited_by_count":7,"area":null},{"id":"2102.00565","title":"CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning","created":"2021-01-31","cited_by_count":5,"area":null},{"id":"2102.05843","title":"Driving Style Representation in Convolutional Recurrent Neural Network Model of Driver Identification","created":"2021-02-11","cited_by_count":5,"area":null},{"id":"2208.12753","title":"Spatio-Temporal Representation Learning Enhanced Source Cell-phone Recognition from Speech Recordings","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2303.10536","title":"TempT: Temporal consistency for Test-time adaptation","created":"2023-03-19","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2208.01753","title":"Two-Stream Transformer Architecture for Long Video Understanding","created":"2022-08-02","cited_by_count":4,"area":null},{"id":"2311.11467","title":"SkateboardAI: The Coolest Video Action Recognition for Skateboarding","created":"2023-08-02","cited_by_count":4,"area":null},{"id":"2111.07370","title":"Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks","created":"2021-11-14","cited_by_count":1,"area":null},{"id":"2203.16163","title":"Rabbit, toad, and the Moon: Can machine categorize them into one class?","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2208.05034","title":"Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework","created":"2022-08-09","cited_by_count":1,"area":null},{"id":"2407.01375","title":"Transferable-guided Attention Is All You Need for Video Domain Adaptation","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2103.10567","title":"CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition","created":"2021-03-18","cited_by_count":0,"area":null},{"id":"2106.03283","title":"Video Imprint","created":"2021-06-07","cited_by_count":0,"area":null}],"next_cursor":null}