{"total":19,"rows":[{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135,"area":null},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103,"area":null},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85,"area":null},{"id":"2303.13519","title":"Learning and Verification of Task Structure in Instructional Videos","created":"2023-03-23","cited_by_count":26,"area":null},{"id":"2308.04369","title":"SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition","created":"2023-08-08","cited_by_count":20,"area":null},{"id":"2107.11639","title":"Self-Conditioned Probabilistic Learning of Video Rescaling","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2403.11021","title":"Towards Neuro-Symbolic Video Understanding","created":"2024-03-16","cited_by_count":16,"area":null},{"id":"2101.06636","title":"Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition","created":"2021-01-17","cited_by_count":14,"area":null},{"id":"2504.17180","title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","created":"2025-04-24","cited_by_count":10,"area":null},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2312.13746","title":"Video Recognition in Portrait Mode","created":"2023-12-21","cited_by_count":6,"area":null},{"id":"2505.13851","title":"A Challenge to Build Neuro-Symbolic Video Agents","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2112.11547","title":"Decompose the Sounds and Pixels, Recompose the Events","created":"2021-12-21","cited_by_count":4,"area":null},{"id":"2209.00990","title":"Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning","created":"2022-08-26","cited_by_count":4,"area":null},{"id":"2105.04143","title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning","created":"2021-05-10","cited_by_count":2,"area":null},{"id":"2511.18701","title":"ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2104.00842","title":"Unconstrained Face Recognition using ASURF and Cloud-Forest Classifier optimized with VLAD","created":"2021-04-02","cited_by_count":0,"area":null},{"id":"2106.03283","title":"Video Imprint","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2110.08063","title":"Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding","created":"2021-10-12","cited_by_count":0,"area":null}],"next_cursor":null}