Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement.

Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics.

Coarse-to-Fine Human Mesh Recovery with Transformers.

Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing Their Contributions.

VEMIC: View-aware Entropy model for Multi-view Image Compression.

NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-Wise Modeling.

Unifying the Harmonic Analysis of Adversarial Attacks and Robustness.

ReLaX: Retinal Layer Attribution for Guided Explanations of Automated Optical Coherence Tomography Classification.

Analyzing and Mitigating JPEG Compression Defects in Deep Learning.

Quantization Guided JPEG Artifact Correction.

Unsupervised Super-Resolution of Satellite Imagery for High Fidelity Material Label Transfer.

Deep Residual Learning in the JPEG Transform Domain.

Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery.

Action-Affect-Gender Classification Using Multi-task Representation Learning.

Facial Attributes Classification Using Multi-task Representation Learning.

Discriminative hand localization in depth images.