Related papers: STVGFormer: Spatio-Temporal Video Grounding with S…
This paper addresses the task of segmenting class-agnostic objects in semi-supervised setting. Although previous detection based methods achieve relatively good performance, these approaches extract the best proposal by a greedy strategy,…
We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion…
Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines. While detecting non-temporal HOIs (e.g., sitting on a chair) from static images is feasible, it is unlikely even for…
Inspired by the performance and scalability of autoregressive large language models (LLMs), transformer-based models have seen recent success in the visual domain. This study investigates a transformer adaptation for video prediction with a…
Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. We think the key to skeleton-based action recognition is a skeleton hanging in frames, so we focus on how the…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…
Considering the inherent stochasticity and uncertainty, predicting future video frames is exceptionally challenging. In this work, we study the problem of video prediction by combining interpretability of stochastic state space models and…
Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise…
Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…
Transformer-based approaches have been successfully proposed for 3D human pose estimation (HPE) from 2D pose sequence and achieved state-of-the-art (SOTA) performance. However, current SOTAs have difficulties in modeling spatial-temporal…
In the field of action recognition, video clips are always treated as ordered frames for subsequent processing. To achieve spatio-temporal perception, existing approaches propose to embed adjacent temporal interaction in the convolutional…
Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of…
Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require…
In order to predict a pedestrian's trajectory in a crowd accurately, one has to take into account her/his underlying socio-temporal interactions with other pedestrians consistently. Unlike existing work that represents the relevant…
This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…
Video-based gaze estimation methods aim to capture the inherently temporal dynamics of human eye gaze from multiple image frames. However, since models must capture both spatial and temporal relationships, performance is limited by the…
Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…
Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation. Our model proceeds on a per-frame basis, guided by the…