Processing

Temporal Relational Modeling with Self-Supervision for Action Segmentation AAAI 2021 Temporal ROI Align for Video Object Recognition AAAI 2021 Terrace-based Food Counting and Segmentation AAAI 2021 Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary Learning CVPR 2021 Text-to-Image Generation Grounded by Fine-Grained User Attention WACV 2021 TF-Blender: Temporal Feature Blender for Video Object Detection ICCV 2021 The Blessings of Unlabeled Background in Untrimmed Videos CVPR 2021 The Boombox: Visual Reconstruction from Acoustic Vibrations CoRL 2021 The Devil Is in the Boundary: Exploiting Boundary Representation for Basis-Based Instance Segmentation WACV 2021 The DKU-Duke-Lenovo System Description for the Fearless Steps Challenge Phase III Interspeech 2021 The Emergence of Objectness: Learning Zero-shot Segmentation from Videos NeurIPS 2021 The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures CVPR 2021 The Image Local Autoregressive Transformer NeurIPS 2021 Themis: A Fair Evaluation Platform for Computer Vision Competitions IJCAI 2021 The Neural Tangent Link Between CNN Denoisers and Non-Local Filters CVPR 2021 The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data ICCV 2021 Three Birds with One Stone: Multi-Task Temporal Action Detection via Recycling Temporal Annotations CVPR 2021 Time Lens: Event-Based Video Frame Interpolation CVPR 2021 Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems ICCV 2021 Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics IJCAI 2021 Topologically Consistent Multi-View Face Inference Using Volumetric Sampling ICCV 2021 Topology-Aware Segmentation Using Discrete Morse Theory ICLR 2021 Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation CVPR 2021 Toward Realistic Virtual Try-on Through Landmark Guided Shape Matching AAAI 2021 Towards a Methodology Supporting Semiautomatic Annotation of HeadMovements in Video-recorded Conversations EMNLP 2021