相关论文: BasicTAD: an Astounding RGB-Only Baseline for Temp…

Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content. Given limited GPU memory, training TAL end to end (i.e., from videos to predictions) on long videos is a…

The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…

Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…

Traffic Accident Anticipation (TAA) in traffic scenes is a challenging problem for achieving zero fatalities in the future. Current approaches typically treat TAA as a supervised learning task needing the laborious annotation of accident…

Video anomaly detection (VAD) -- commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature -- is a challenging problem in video surveillance where the frames of anomaly need…

Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise video matching. While the frame- and tuple-level alignment…

Fusing Events and RGB images for object detection leverages the robustness of Event cameras in adverse environments and the rich semantic information provided by RGB cameras. However, two critical mismatches: low-latency Events…

In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video. Specifically, given an untrimmed video, WSSTAD aims to localize a spatio-temporal tube (i.e., a…

Current approaches to 3D scene graph generation rely on dedicated depth sensors, such as LiDAR or RGB-D cameras, for metric 3D reconstruction. This limits deployment to specialized robotic platforms and excludes settings where only RGB…

We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for…

Face presentation attack detection (PAD) plays an important role in defending face recognition systems against presentation attacks. The success of PAD largely relies on supervised learning that requires a huge number of labeled data, which…

Graph anomaly detection (GAD) has attracted increasing attention in recent years for identifying malicious samples in a wide range of graph-based applications, such as social media and e-commerce. However, most GAD methods assume identical…

The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural…

Time series anomaly detection (TSAD) has been a research hotspot in both academia and industry in recent years. Deep learning methods have become the mainstream research direction due to their excellent performance. However, new viewpoints…

Reliable 4D object detection, which refers to 3D object detection in streaming video, is crucial for perceiving and understanding the real world. Existing open-set 4D object detection methods typically make predictions on a frame-by-frame…

This paper introduces TACTIC-GRAPHS, a system that combines spectral graph theory and multimodal graph neural reasoning for semantic understanding and threat detection in tactical video under high noise and weak structure. The framework…

Existing RGB-D SOD methods mainly rely on a symmetric two-stream CNN-based network to extract RGB and depth channel features separately. However, there are two problems with the symmetric conventional network structure: first, the ability…

We introduce the task of human action anomaly detection (HAAD), which aims to identify anomalous motions in an unsupervised manner given only the pre-determined normal category of training action samples. Compared to prior human-related…

Fault detection is essential in complex industrial systems to prevent failures and optimize performance by distinguishing abnormal from normal operating conditions. With the growing availability of condition monitoring data, data-driven…

Video Temporal Grounding (VTG) aims to extract relevant video segments based on a given natural language query. Recently, zero-shot VTG methods have gained attention by leveraging pretrained vision-language models (VLMs) to localize target…