相关论文: Connectionist Temporal Modeling for Weakly Supervi…

Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require…

Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset.…

Temporal sentence grounding aims to detect the event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great performance but requires expensive annotation costs;…

Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically…

In industrial settings, weakly supervised (WS) methods are usually preferred over their fully supervised (FS) counterparts as they do not require costly manual annotations. Unfortunately, the segmentation masks obtained in the WS regime are…

We address the problem of temporal localization of repetitive activities in a video, i.e., the problem of identifying all segments of a video that contain some sort of repetitive or periodic motion. To do so, the proposed method represents…

Dense anticipation aims to forecast future actions and their durations for long horizons. Existing approaches rely on fully-labelled data, i.e. sequences labelled with all future actions and their durations. We present a (semi-) weakly…

We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the first discriminative…

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…

Temporal action segmentation (TAS) aims to classify and locate actions in the long untrimmed action sequence. With the success of deep learning, many deep models for action segmentation have emerged. However, few-shot TAS is still a…

We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels which specify the object classes present in the image. Our method uses deep convolutional neural networks (CNNs) and…

Detecting actions in videos have been widely applied in on-device applications. Practical on-device videos are always untrimmed with both action and background. It is desirable for a model to both recognize the class of action and localize…

Video representation learning has been successful in video-text pre-training for zero-shot transfer, where each sentence is trained to be close to the paired video clips in a common feature space. For long videos, given a paragraph of…

A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in…

Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data…

Instrument playing is among the most common scenes in music-related videos, which represent nowadays one of the largest sources of online videos. In order to understand the instrument-playing scenes in the videos, it is important to know…

Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive…

This paper aims at recognizing partially observed human actions in videos. Action videos acquired in uncontrolled environments often contain corrupt frames, which make actions partially observed. Furthermore, these frames can last for…