相关论文: Diversifying Spatial-Temporal Perception for Video…

Accuracy of depth estimation from static images has been significantly improved recently, by exploiting hierarchical features from deep convolutional neural networks (CNNs). Compared with static images, vast information exists among video…

In the light of exponentially increasing video content, video summarization has attracted a lot of attention recently due to its ability to optimize time and storage. Characteristics of a good summary of a video depend on the particular…

Recognition across domains has recently become an active topic in the research community. However, it has been largely overlooked in the problem of recognition in new unseen domains. Under this condition, the delivered deep network models…

Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to…

With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn…

Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for…

Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area due to the significant spatial and temporal shifts across the source (i.e. training)…

This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…

Majority of state-of-the-art monocular depth estimation methods are supervised learning approaches. The success of such approaches heavily depends on the high-quality depth labels which are expensive to obtain. Some recent methods try to…

We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequential data, our main idea is to use Long Short-Term…

We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual…

Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene…

Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e.,…

Recent studies have proven that DNNs, unlike human vision, tend to exploit texture information rather than shape. Such texture bias is one of the factors for the poor generalization performance of DNNs. We observe that the texture bias…

Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous human actions. Although Selective State Space Models (SSMs)…

Video moment retrieval pursues an efficient and generalized solution to identify the specific temporal segments within an untrimmed video that correspond to a given language description. To achieve this goal, we provide a generative…

Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…

Domain generalization typically requires data from multiple source domains for model learning. However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and…

Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework…

Deep learning models heavily rely on large scale annotated datasets for training. Unfortunately, datasets cannot capture the infinite variability of the real world, thus neural networks are inherently limited by the restricted visual and…