Related papers: Hierarchical Semantic Contrast for Scene-aware Vid…
Hyperspectral images are high-dimensional datasets comprising hundreds of contiguous spectral bands, enabling detailed analysis of materials and surfaces. Hyperspectral anomaly detection (HAD) refers to the technique of identifying and…
Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. However, current approaches are inherently limited to a…
Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and…
Human-object interaction recognition aims for identifying the relationship between a human subject and an object. Researchers incorporate global scene context into the early layers of deep Convolutional Neural Networks as a solution. They…
For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…
Compression artifacts from standard video codecs often degrade perceptual quality. We propose a lightweight, semantic-aware pre-processing framework that enhances perceptual fidelity by selectively addressing these distortions. Our method…
In recent years, video analysis using Artificial Intelligence (AI) has been widely used, due to the remarkable development of image recognition technology using deep learning. In 2019, the Moving Picture Experts Group (MPEG) has started…
Video captioning is a challenging task that captures different visual parts and describes them in sentences, for it requires visual and linguistic coherence. The attention mechanism in the current video captioning method learns to assign…
Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and…
Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when…
Scene graph parsing aims to detect objects in an image scene and recognize their relations. Recent approaches have achieved high average scores on some popular benchmarks, but fail in detecting rare relations, as the highly long-tailed…
In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be…
Ensuring validation for highly automated driving poses significant obstacles to the widespread adoption of highly automated vehicles. Scenario-based testing offers a potential solution by reducing the homologation effort required for these…
Anomaly detection and localization without any manual annotations and prior knowledge is a challenging task under the setting of unsupervised learning. The existing works achieve excellent performance in the anomaly detection, but with…
Video anomaly detection has proved to be a challenging task owing to its unsupervised training procedure and high spatio-temporal complexity existing in real-world scenarios. In the absence of anomalous training samples, state-of-the-art…
Existing deep learning methods of video recognition usually require a large number of labeled videos for training. But for a new task, videos are often unlabeled and it is also time-consuming and labor-intensive to annotate them. Instead of…
Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data…
One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many…
We propose an architecture and training scheme to predict video frames by explicitly modeling dis-occlusions and capturing the evolution of semantically consistent regions in the video. The scene layout (semantic map) and motion (optical…
Existing video anomaly detection datasets are inadequate for representing complex anomalies that occur due to the interactions between objects. The absence of complex anomalies in previous video anomaly detection datasets affects research…