Related papers: Motion meets Attention: Video Motion Prompts
We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial…
Visual anomaly detection in multi-class settings poses significant challenges due to the diversity of object categories, the scarcity of anomalous examples, and the presence of camouflaged defects. In this paper, we propose PromptMAD, a…
Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection in untrimmed security…
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features…
From an image sequence captured by a stationary camera, background subtraction can detect moving foreground objects in the scene. Distinguishing foreground from background is further improved by various heuristics. Then each object's motion…
A variety of attention mechanisms have been studied to improve the performance of various computer vision tasks. However, the prior methods overlooked the significance of retaining the information on both channel and spatial aspects to…
Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the…
This paper is on video recognition using Transformers. Very recent attempts in this area have demonstrated promising results in terms of recognition accuracy, yet they have been also shown to induce, in many cases, significant computational…
We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation. MAMP leverages the frame reconstruction task for training without the need for annotations. During…
Automatic instrument segmentation in video is an essentially fundamental yet challenging problem for robot-assisted minimally invasive surgery. In this paper, we propose a novel framework to leverage instrument motion information, by…
We present an active visual search model for finding objects in unknown environments. The proposed algorithm guides the robot towards the sought object using the relevant stimuli provided by the visual sensors. Existing search strategies…
Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their…
Spatio-temporal contexts are crucial in understanding human actions in videos. Recent state-of-the-art Convolutional Neural Network (ConvNet) based action recognition systems frequently involve 3D spatio-temporal ConvNet filters, chunking…
Interactive segmentation algorithms based on click points have garnered significant attention from researchers in recent years. However, existing studies typically use sparse click maps as model inputs to segment specific target objects,…
We propose a novel guided interactive segmentation (GIS) algorithm for video objects to improve the segmentation accuracy and reduce the interaction time. First, we design the reliability-based attention module to analyze the reliability of…
Surveillance footage can catch a wide range of realistic anomalies. This research suggests using a weakly supervised strategy to avoid annotating anomalous segments in training videos, which is time consuming. In this approach only video…
Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective modules to precisely localize action instances based on appearance and motion features. However, by…
Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation…
We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models. Rather than treating all video content uniformly, our method dynamically adjusts temporal…
Existing person video generation methods either lack the flexibility in controlling both the appearance and motion, or fail to preserve detailed appearance and temporal consistency. In this paper, we tackle the problem of motion transfer…