We present a new multi-view depth estimation method that utilizes both conventional SfM reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF).

We propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process.

We propose to learn a neural structure extractor unsupervisedly to extract structural patterns in images and use it to supervise SR models.

We present a deep interpretable metric learning (DIML) that adopts a structural matching strategy to explicitly aligns the spatial embeddings by computing an optimal matching flow between feature maps of the two images.

We propose a new contrastive regression (CoRe) framework to learn the relative scores by pair-wise comparison, which highlights the differences between videos and guides the models to learn the key hints for action quality assessment.

We present point-voxel correlation fields for 3D scene flow estimation which migrates the high performance of RAFT and provides a solution to build structured all-pairs correlation fields for unstructured point clouds.

We present a new Multi-Proxy Wasserstein Classifier to imporve the image classification models by calculating a non-uniform matching flow between the elements in the feature map of a sample and multiple proxies of a class using optimal transport theory.

We show temporal coherence plays a more critical role than temporal motion for video-based person re-identification and develop a Adversarial Feature Augmentation (AFA) to highlight temporal coherence.

We boost the performance of CNNs by learning soft targets for shallow layers via meta-learning.

We propose to leverage gradient information as an extra supervision signal to restore structures while generating natural SR images.

We propose a deep face super-resolution method with iterative collaboration between two recurrent networks which focus on facial image recovery and landmark estimation respectively

COIN is the largest and most comprehensive instructional video analysis dataset with rich annotations.

We propose a discriminative aggregation network (DAN) method for video-based face recognition and person re-identification, which aims to integrate information from video frames for feature representation effectively and efficiently.

We propose a simple yet effective method to learn globally optimized detector for object detection by directly optimizing mAP using the REINFORCE algorithm.

We propose a Runtime Neural Pruning (RNP) framework which prunes the deep neural network dynamically at the runtime.

We propose a discriminative aggregation network (DAN) method for video face recognition, which aims to integrate information from video frames effectively and efficiently.

We propose an attention-aware deep reinforcement learning (ADRL) method for video face recognition, which aims to discard the misleading and confounding frames and find the focuses of attentions in face videos for person recognition.

We propose a new tree structure for moving objects kNN search with road-network constraints, which can be used in many real-world applications like taxi search.