Related papers: Dynamic Face Video Segmentation via Reinforcement …

Semantic segmentation is an important task in computer vision, from which some important usage scenarios are derived, such as autonomous driving, scene parsing, etc. Due to the emphasis on the task of video semantic segmentation, we…

Surface crack segmentation poses a challenging computer vision task as background, shape, colour and size of cracks vary. In this work we propose optimized deep encoder-decoder methods consisting of a combination of techniques which yield…

Training deep neural networks typically requires large amounts of labeled data which may be scarce or expensive to obtain for a particular target domain. As an alternative, we can leverage webly-supervised data (i.e. results from a public…

Instance segmentation is a fundamental task in computer vision with broad applications across various industries. In recent years, with the proliferation of deep learning and artificial intelligence applications, how to train effective…

Video compression has always been a popular research area, where many traditional and deep video compression methods have been proposed. These methods typically rely on signal prediction theory to enhance compression performance by…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose…

Image segmentation needs both local boundary position information and global object context information. The performance of the recent state-of-the-art method, fully convolutional networks, reaches a bottleneck due to the neural network…

Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different…

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…

Evolutionary algorithms, such as Differential Evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts…

We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup. Our method consists of two distinct components, one of which focuses on…

Action segmentation is the task of temporally segmenting every frame of an untrimmed video. Weakly supervised approaches to action segmentation, especially from transcripts have been of considerable interest to the computer vision…

Most existing video summarisation methods are based on either supervised or unsupervised learning. In this paper, we propose a reinforcement learning-based weakly supervised method that exploits easy-to-obtain, video-level category labels…

In recent years, video semantic segmentation has made great progress with advanced deep neural networks. However, there still exist two main challenges \ie, information inconsistency and computation cost. To deal with the two difficulties,…

Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…

As a fundamental task in computer vision, semantic segmentation is widely applied in fields such as autonomous driving, remote sensing image analysis, and medical image processing. In recent years, Transformer-based segmentation methods…

Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action…

The existing action recognition methods are mainly based on clip-level classifiers such as two-stream CNNs or 3D CNNs, which are trained from the randomly selected clips and applied to densely sampled clips during testing. However, this…

Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…