相关论文: Weak Supervision and Referring Attention for Tempo…
Weakly supervised video grounding aims to localize temporal boundaries relevant to a given query without explicit ground-truth temporal boundaries. While existing methods primarily use Gaussian-based proposals, they overlook the importance…
Automatic estimation of pain intensity from facial expressions in videos has an immense potential in health care applications. However, domain adaptation (DA) is needed to alleviate the problem of domain shifts that typically occurs between…
In this work we study Weakly Supervised Spatio-Temporal Video Grounding (WSTVG), a challenging task of localizing subjects spatio-temporally in videos using only textual queries and no bounding box supervision. Inspired by recent advances…
In this work, we address the task of weakly-supervised human action segmentation in long, untrimmed videos. Recent methods have relied on expensive learning models, such as Recurrent Neural Networks (RNN) and Hidden Markov Models (HMM).…
Diagnostic and intervention methodologies for skill assessment of autism typically requires a clinician repetitively initiating several stimuli and recording the child's response. In this paper, we propose to automate the response…
Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG approaches are…
We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with…
Video moment retrieval aims to localize the target moment in an video according to the given sentence. The weak-supervised setting only provides the video-level sentence annotations during training. Most existing weak-supervised methods…
Video captioning has shown impressive progress in recent years. One key reason of the performance improvements made by existing methods lie in massive paired video-sentence data, but collecting such strong annotation, i.e., high-quality…
We study weakly-supervised video object grounding: given a video segment and a corresponding descriptive sentence, the goal is to localize objects that are mentioned from the sentence in the video. During training, no object bounding boxes…
Video captioning is a challenging task that captures different visual parts and describes them in sentences, for it requires visual and linguistic coherence. The attention mechanism in the current video captioning method learns to assign…
We propose a weakly-supervised framework for action labeling in video, where only the order of occurring actions is required during training time. The key challenge is that the per-frame alignments between the input (video) and label…
Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…
Weakly supervised referring expression grounding aims at localizing the referential object in an image according to the linguistic query, where the mapping between the referential object and query is unknown in the training stage. To…
The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or…
We describe a latent approach that learns to detect actions in long sequences given training videos with only whole-video class labels. Our approach makes use of two innovations to attention-modeling in weakly-supervised learning. First,…
Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard…
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 is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and…
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…