Related papers: Forcing the Whole Video as Background: An Adversar…
For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are…
This paper presents a simple yet effective approach for the poorly investigated task of global action segmentation, aiming at grouping frames capturing the same action across videos of different activities. Unlike the case of videos…
Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to fully exploit multi-resolution…
Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain. To relieve the burden of data…
We present a semi-supervised learning approach to the temporal action segmentation task. The goal of the task is to temporally detect and segment actions in long, untrimmed procedural videos, where only a small set of videos are densely…
Point-level weakly-supervised temporal action localization (PWTAL) aims to localize actions with only a single timestamp annotation for each action instance. Existing methods tend to mine dense pseudo labels to alleviate the label sparsity,…
Temporal action segmentation classifies the action of each frame in (long) video sequences. Due to the high cost of frame-wise labeling, we propose the first semi-supervised method for temporal action segmentation. Our method hinges on…
Temporal action localization (TAL) is a task of identifying a set of actions in a video, which involves localizing the start and end frames and classifying each action instance. Existing methods have addressed this task by using predefined…
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly…
Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent advancements in this field focus on developing more…
Understanding human behavior is an important problem in the pursuit of visual intelligence. A challenge in this endeavor is the extensive and costly effort required to accurately label action segments. To address this issue, we consider…
Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from…
Action recognition has become a rapidly developing research field within the last decade. But with the increasing demand for large scale data, the need of hand annotated data for the training becomes more and more impractical. One way to…
Since collecting and annotating data for spatio-temporal action detection is very expensive, there is a need to learn approaches with less supervision. Weakly supervised approaches do not require any bounding box annotations and can be…
Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised…
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…
Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. First, fast adversarial…
Weakly supervised temporal action localization is a newly emerging yet widely studied topic in recent years. The existing methods can be categorized into two localization-by-classification pipelines, i.e., the pre-classification pipeline…
This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization…
Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…