相关论文: Adaptive Focus for Efficient Video Recognition

This paper addresses fast semantic segmentation on video.Video segmentation often calls for real-time, or even fasterthan real-time, processing. One common recipe for conserving computation arising from feature extraction is to propagate…

The Video comprises approximately ~85\% of all internet traffic, but video encoding/compression is being historically done with hard coded rules, which has worked well but only to a certain limit. We have seen a surge in video compression…

Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action…

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but…

Spatial convolutions are widely used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions…

Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides…

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence,…

Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In this paper, we rethink that the redundancy in inversion-based…

Developing end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding. Due to the unaffordable cost of end-to-end training on the whole long videos, existing works generally train…

Optimizing video inference efficiency has become increasingly important with the growing demand for video analysis in various fields. Some existing methods achieve high efficiency by explicit discard of spatial or temporal information,…

Object detection in videos is an important task in computer vision for various applications such as object tracking, video summarization and video search. Although great progress has been made in improving the accuracy of object detection…

Interpreting human actions requires understanding the spatial and temporal context of the scenes. State-of-the-art action detectors based on Convolutional Neural Network (CNN) have demonstrated remarkable results by adopting two-stream or…

The state of the art in video understanding suffers from two problems: (1) The major part of reasoning is performed locally in the video, therefore, it misses important relationships within actions that span several seconds. (2) While there…

Learning image representations with ConvNets by pre-training on ImageNet has proven useful across many visual understanding tasks including object detection, semantic segmentation, and image captioning. Although any image representation can…

Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significantly to their high performance. However, it is known to incur…

This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…

Convolutional neural network inference on video data requires powerful hardware for real-time processing. Given the inherent coherence across consecutive frames, large parts of a video typically change little. By skipping identical image…

Most video restoration networks are slow, have high computational load, and can't be used for real-time video enhancement. In this work, we design an efficient and fast framework to perform real-time video enhancement for practical…

This paper tackles the problem of motion deblurring of dynamic scenes. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is…