Related papers: Exploiting Motion Information from Unlabeled Video…
Data augmentation is a ubiquitous technique for improving image classification when labeled data is scarce. Constraining the model predictions to be invariant to diverse data augmentations effectively injects the desired representational…
Vision-Language-Action (VLA) models have gained popularity for learning robotic manipulation tasks that follow language instructions. State-of-the-art VLAs, such as OpenVLA and $\pi_{0}$, were trained on large-scale, manually labeled action…
Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities…
Although synthetic training data has been shown to be beneficial for tasks such as human pose estimation, its use for RGB human action recognition is relatively unexplored. Our goal in this work is to answer the question whether synthetic…
Identifying highlight moments of raw video materials is crucial for improving the efficiency of editing videos that are pervasive on internet platforms. However, the extensive work of manually labeling footage has created obstacles to…
Realistic videos of human actions exhibit rich spatiotemporal structures at multiple levels of granularity: an action can always be decomposed into multiple finer-grained elements in both space and time. To capture this intuition, we…
Motions are reflected in videos as the movement of pixels, and actions are essentially patterns of inconsistent motions between the foreground and the background. To well distinguish the actions, especially those with complicated…
We propose an unsupervised method for detecting and tracking moving objects in 3D, in unlabelled RGB-D videos. The method begins with classic handcrafted techniques for segmenting objects using motion cues: we estimate optical flow and…
Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain…
In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data. We propose a simple end-to-end consistency based approach which effectively utilizes the unlabeled data.…
Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation…
This work introduces verb-only representations for both recognition and retrieval of visual actions, in video. Current methods neglect legitimate semantic ambiguities between verbs, instead choosing unambiguous subsets of verbs along with…
Multi-label multi-view action recognition aims to recognize multiple concurrent or sequential actions from untrimmed videos captured by multiple cameras. Existing work has focused on multi-view action recognition in a narrow area with…
Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision datasets that predominantly have a stationary camera. If these…
Constructing supervised machine learning models for real-world video analysis require substantial labeled data, which is costly to acquire due to scarce domain expertise and laborious manual inspection. While data programming shows promise…
Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been…
Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet. However, for video action recognition, the action of…
Human action recognition refers to automatic recognizing human actions from a video clip. In reality, there often exist multiple human actions in a video stream. Such a video stream is often weakly-annotated with a set of relevant human…
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…
Video action recognition is a challenging but important task for understanding and discovering what the video does. However, acquiring annotations for a video is costly, and semi-supervised learning (SSL) has been studied to improve…