Image and video content analysis

DQFORMER: DYNAMIC QUERY TRANSFORMER FOR LANE DETECTION

Lightweight Portrait Segmentation via Edge-optimized Attention

Mutual Information based Reweighting for Precipitation Nowcasting

Streaming Stroke Classification of Online Handwriting

Long-tailed Recognition with Causal Invariant Transformation

Decaying Contrast for Fine-grained Video Representation Learning

Nasty-SFDA: Source Free Domain Adaptation from A Nasty Model

Deep Double Self-expressive Subspace Clustering

FREQUENCY-AWARE ATTENTIONAL FEATURE FUSION FOR DEEPFAKE DETECTION

Towards Improved Room Impulse Response Estimation for Speech Recognition

2DSBG: A 2D SEMI BI-GAUSSIAN FILTER ADAPTED FOR ADJACENT AND MULTI-SCALE LINE FEATURE DETECTION

Overcoming Posterior Collapse in Variational Autoencoders via EM-type Training