Related papers: STMixer: A One-Stage Sparse Action Detector
Accurate and efficient perception is essential for autonomous driving, where segmentation tasks such as drivable-area and lane segmentation provide critical cues for motion planning and control. However, achieving high segmentation accuracy…
A fundamental challenge in machine learning today is to build a model that can learn from few examples. Here, we describe a reservoir based spiking neural model for learning to recognize actions with a limited number of labeled videos.…
Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data. In this paper, a novel video based action recognition framework utilizing complementary cues is proposed to handle…
With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…
Video snapshot compressive imaging (SCI) captures multiple sequential video frames by a single measurement using the idea of computational imaging. The underlying principle is to modulate high-speed frames through different masks and these…
In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these…
State space models (SSMs) have emerged as a competitive alternative to transformers in various tasks. Their linear complexity and hidden-state recurrence make them particularly attractive for modeling long sequences, whereas attention…
3D action recognition is referred to as the classification of action sequences which consist of 3D skeleton joints. While many research work are devoted to 3D action recognition, it mainly suffers from three problems: highly complicated…
This paper addresses the problem of spatiotemporal localization of actions in videos. Compared to leading approaches, which all learn to localize based on carefully annotated boxes on training video frames, we adhere to a weakly-supervised…
It's common for current methods in skeleton-based action recognition to mainly consider capturing long-term temporal dependencies as skeleton sequences are typically long (>128 frames), which forms a challenging problem for previous…
Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame…
In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected discriminative frames and the…
In this paper, we propose Two-Stream AMTnet, which leverages recent advances in video-based action representation[1] and incremental action tube generation[2]. Majority of the present action detectors follow a frame-based representation, a…
As both computer vision models and biomedical datasets grow in size, there is an increasing need for efficient inference algorithms. We utilize cascade detectors to efficiently identify sparse objects in multiresolution images. Given an…
Human-human motion generation is essential for understanding humans as social beings. Current methods fall into two main categories: single-person-based methods and separate modeling-based methods. To delve into this field, we abstract the…
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common…
Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image…
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…
For safety-critical robotics applications such as autonomous driving, it is important to detect all required objects accurately in real-time. Motion segmentation offers a solution by identifying dynamic objects from the scene in a…
Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamically selects a few…