Related papers: A new way of video compression via forward-referen…
Predicting future human behavior from an input human video is a useful task for applications such as autonomous driving and robotics. While most previous works predict a single future, multiple futures with different behavior can…
Deep generative models, and particularly facial animation schemes, can be used in video conferencing applications to efficiently compress a video through a sparse set of keypoints, without the need to transmit dense motion vectors. While…
With the advancement in computer vision deep learning, systems now are able to analyze an unprecedented amount of rich visual information from videos to enable applications such as autonomous driving, socially-aware robot assistant and…
Recent years have witnessed the significant development of learning-based video compression methods, which aim at optimizing objective or perceptual quality and bit rates. In this paper, we introduce deep video compression with perceptual…
In this paper, we propose to learn temporal embeddings of video frames for complex video analysis. Large quantities of unlabeled video data can be easily obtained from the Internet. These videos possess the implicit weak label that they are…
The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video…
Standard video encoders developed for conventional narrow field-of-view video are widely applied to 360{\deg} video as well, with reasonable results. However, while this approach commits arbitrarily to a projection of the spherical frames,…
Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular structure and complex dynamics. In this paper, we propose a…
Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single neighboring frame or a pair of neighboring frames (preceding and/or following the target…
Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it's difficult to train any neural network in front of the encoder for gradient's…
While most neural video codecs address P-frame coding (predicting each frame from past ones), in this paper we address B-frame compression (predicting frames using both past and future reference frames). Our B-frame solution is based on the…
This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature prediction, we argue that a supervisory signal arising from…
Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual…
Training robust deep video representations has proven to be computationally challenging due to substantial decoding overheads, the enormous size of raw video streams, and their inherent high temporal redundancy. Different from existing…
Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based…
The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…
Video prediction, forecasting the future frames from a sequence of input frames, is a challenging task since the view changes are influenced by various factors, such as the global context surrounding the scene and local motion dynamics. In…
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local…
Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…
We propose a lightweight compressed-domain tracking model that operates directly on video streams, without requiring full RGB video decoding. Using motion vectors and transform coefficients from compressed data, our deep model propagates…