Related papers: Distilling Aggregated Knowledge for Weakly-Supervi…

Monocular depth estimation is challenging due to its inherent ambiguity and ill-posed nature, yet it is quite important to many applications. While recent works achieve limited accuracy by designing increasingly complicated networks to…

Vision Transformers (ViTs) have achieved strong performance in video action recognition, but their high computational cost limits their practicality. Lightweight CNNs are more efficient but suffer from accuracy gaps. Cross-Architecture…

High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher…

Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant…

Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A hurdle of training event-based models is the lack of large…

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and…

One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection…

Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each…

To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting).…

Skeleton-based action recognition is vital for comprehending human-centric videos and has applications in diverse domains. One of the challenges of skeleton-based action recognition is dealing with low-quality data, such as skeletons that…

Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However, most KD methods require a large training set and internal…

Graph anomaly detection is critical in domains such as healthcare and economics, where identifying deviations can prevent substantial losses. Existing unsupervised approaches strive to learn a single model capable of detecting both…

Anomaly detection consists in identifying, within a dataset, those samples that significantly differ from the majority of the data, representing the normal class. It has many practical applications, e.g. ranging from defective product…

In this research we propose a deep learning approach for detecting anomalies in videos using convolutional autoencoder and decoder neural networks on the UCSD dataset.Our method utilizes a convolutional autoencoder to learn the…

Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the…

We propose a lightweight and accurate method for detecting anomalies in videos. Existing methods used multiple-instance learning (MIL) to determine the normal/abnormal status of each segment of the video. Recent successful researches argue…

Knowledge distillation has emerged as a powerful technique for model compression, enabling the transfer of knowledge from large teacher networks to compact student models. However, traditional knowledge distillation methods treat all…

Recent weakly supervised video anomaly detection methods have achieved significant advances by employing unified frameworks for joint optimization. However, this paradigm is limited by a fundamental sensitivity-stability trade-off, as the…

The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driving. Motivated by the success of Convolutional Neural…

Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i.e., uniform). To tackle the consequent cross-distribution generalization concerns, we bring the knowledge…