Related papers: PTSEFormer: Progressive Temporal-Spatial Enhanced …
Existing methods of multi-person video 3D human Pose and Shape Estimation (PSE) typically adopt a two-stage strategy, which first detects human instances in each frame and then performs single-person PSE with temporal model. However, the…
Remote photoplethysmography (rPPG), which aims at measuring heart activities and physiological signals from facial video without any contact, has great potential in many applications (e.g., remote healthcare and affective computing). Recent…
Audio-visual emotion recognition (AVER) methods typically fuse utterance-level features, and even frame-level attention models seldom address the frame-rate mismatch across modalities. In this paper, we propose a Transformer-based framework…
We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To…
In this paper, we propose a new Transformer block for video future frames prediction based on an efficient local spatial-temporal separation attention mechanism. Based on this new Transformer block, a fully autoregressive video future…
As drone technology advances, using unmanned aerial vehicles for aerial surveys has become the dominant trend in modern low-altitude remote sensing. The surge in aerial video data necessitates accurate prediction for future scenarios and…
Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…
Semantic segmentation of night-time images holds significant importance in computer vision, particularly for applications like night environment perception in autonomous driving systems. However, existing methods tend to parse night-time…
Face analysis has been studied from different angles to infer emotion, poses, shapes, and landmarks. Traditionally RGB cameras are used, yet for fine-grained tasks standard sensors might not be up to the task due to their latency, making it…
This paper addresses the problem of how to exploit spatio-temporal information available in videos to improve the object detection precision. We propose a two stage object detector called FANet based on short-term spatio-temporal feature…
Adapting image-pretrained backbones to video typically relies on time-domain adapters tuned to a single temporal scale. Our experiments show that these modules pick up static image cues and very fast flicker changes, while overlooking…
Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into…
Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…
Pedestrian Detection is the most critical module of an Autonomous Driving system. Although a camera is commonly used for this purpose, its quality degrades severely in low-light night time driving scenarios. On the other hand, the quality…
Vision Transformers (ViTs) have recently achieved state-of-the-art performance in 2D human pose estimation due to their strong global modeling capability. However, existing ViT-based pose estimators are designed for static images and…
In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos. Starting from a handful of coarse-scale proposal cuboids, our approach…
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory…
Most modern approaches in temporal action localization divide this problem into two parts: (i) short-term feature extraction and (ii) long-range temporal boundary localization. Due to the high GPU memory cost caused by processing long…
4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the…
Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…