Vision-based traffic accident detection and anticipation: A survey
Traffic accident detection and anticipation is an obstinate road safety problem and
painstaking efforts have been devoted. With the rapid growth of video data, Vision-based …
painstaking efforts have been devoted. With the rapid growth of video data, Vision-based …
Removing anomalies as noises for industrial defect localization
Unsupervised anomaly detection aims to train models with only anomaly-free images to
detect and localize unseen anomalies. Previous reconstruction-based methods have been …
detect and localize unseen anomalies. Previous reconstruction-based methods have been …
Task-driven causal feature distillation: Towards trustworthy risk prediction
Since artificial intelligence has seen tremendous recent successes in many areas, it has
sparked great interest in its potential for trustworthy and interpretable risk prediction …
sparked great interest in its potential for trustworthy and interpretable risk prediction …
Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network?
A rising trend in theoretical deep learning is to understand why deep learning works through
Neural Tangent Kernel (NTK)[jgh18], a kernel method that is equivalent to using gradient …
Neural Tangent Kernel (NTK)[jgh18], a kernel method that is equivalent to using gradient …
Vaquita: Enhancing alignment in llm-assisted video understanding
Recent advancements in language-model-based video understanding have been
progressing at a remarkable pace, spurred by the introduction of Large Language Models …
progressing at a remarkable pace, spurred by the introduction of Large Language Models …
Ada-VAD: Domain Adaptable Video Anomaly Detection
Video anomaly detection (VAD) aims at identifying unusual behaviors from videos. Most of
the existing video anomaly detection methods can achieve promising performance in the …
the existing video anomaly detection methods can achieve promising performance in the …
Momentum is All You Need for Data-Driven Adaptive Optimization
Adaptive gradient methods, eg, ADAM, have achieved tremendous success in data-driven
machine learning, especially deep learning. Employing adaptive learning rates according to …
machine learning, especially deep learning. Employing adaptive learning rates according to …
Towards Zero-shot 3D Anomaly Localization
3D anomaly detection and localization is of great significance for industrial inspection. Prior
3D anomaly detection and localization methods focus on the setting that the testing data …
3D anomaly detection and localization methods focus on the setting that the testing data …
VaQuitA: Enhancing Alignment in LLM-Assisted Zero-Shot Video Understanding
Recent advancements in language-model-based video understanding have been
progressing at a remarkable pace, spurred by the introduction of Large Language Models …
progressing at a remarkable pace, spurred by the introduction of Large Language Models …