{"total":19,"rows":[{"id":"2211.09980","title":"Contrastive Positive Sample Propagation along the Audio-Visual Event Line","created":"2022-11-18","cited_by_count":50,"area":null},{"id":"2112.08995","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","created":"2021-12-16","cited_by_count":17,"area":null},{"id":"2110.02011","title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2103.01746","title":"Comparison of Methods Generalizing Max- and Average-Pooling","created":"2021-03-02","cited_by_count":6,"area":null},{"id":"2505.01109","title":"Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study","created":"2025-05-02","cited_by_count":6,"area":null},{"id":"2106.06858","title":"Improving weakly supervised sound event detection with self-supervised auxiliary tasks","created":"2021-06-12","cited_by_count":4,"area":null},{"id":"2109.14061","title":"The impact of non-target events in synthetic soundscapes for sound event detection","created":"2021-09-28","cited_by_count":4,"area":null},{"id":"2102.03468","title":"Sound Event Detection in Urban Audio With Single and Multi-Rate PCEN","created":"2021-02-06","cited_by_count":3,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2510.21038","title":"Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2104.09021","title":"Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution","created":"2021-04-19","cited_by_count":1,"area":null},{"id":"2206.12494","title":"Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2312.14005","title":"On the choice of the optimal temporal support for audio classification with Pre-trained embeddings","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2502.09363","title":"The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2507.18334","title":"Improving Bird Classification with Primary Color Additives","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2509.16715","title":"QASTAnet: A DNN-based Quality Metric for Spatial Audio","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2602.01850","title":"WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2606.10627","title":"Profy: Interpretable Visualization of Expertise-Dependent Motor Skills Toward Supporting Piano Practice","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.22136","title":"DiFA: Dual Evidence Fusion and Aggregation for Token-Level Text Anomaly Detection","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}