Related papers: Global2Local: Efficient Structure Search for Video…
Deep neural networks have achieved great success for video analysis and understanding. However, designing a high-performance neural architecture requires substantial efforts and expertise. In this paper, we make the first attempt to let…
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…
Referring video object segmentation aims to segment a referent throughout a video sequence according to a natural language expression. It requires aligning the natural language expression with the objects' motions and their dynamic…
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…
Detecting and segmenting novel object instances in open-world environments is a fundamental problem in robotic perception. Given only a small set of template images, a robot must locate and segment a specific object instance in a cluttered,…
In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…
Sports videos pose complex challenges, including cluttered backgrounds, camera angle changes, small action-representing objects, and imbalanced action class distribution. Existing methods for detecting actions in sports videos heavily rely…
Generating high-fidelity 3D indoor scenes remains a significant challenge due to data scarcity and the complexity of modeling intricate spatial relations. Current methods often struggle to scale beyond training distribution to dense scenes…
Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the…
This work presents a first evaluation of using spatio-temporal receptive fields from a recently proposed time-causal spatio-temporal scale-space framework as primitives for video analysis. We propose a new family of video descriptors based…
As research on action recognition matures, the focus is shifting away from categorizing basic task-oriented actions using hand-segmented video datasets to understanding complex goal-oriented daily human activities in real-world settings.…
Spatial and temporal relationships, both short-range and long-range, between objects in videos, are key cues for recognizing actions. It is a challenging problem to model them jointly. In this paper, we first present a new variant of Long…
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features…
We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance…
Most existing video moment retrieval methods rely on temporal sequences of frame- or clip-level features that primarily encode global visual and semantic information. However, such representations often fail to capture fine-grained object…
Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks. Yet neither stacks of convolutional operations to enlarge receptive fields nor recent…
Multimodal recommendation systems can learn users' preferences from existing user-item interactions as well as the semantics of multimodal data associated with items. Many existing methods model this through a multimodal user-item graph,…
Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient…
Because of the variabilities of real-world image structures under the natural image transformations that arise when observing similar objects or spatio-temporal events under different viewing conditions, the receptive field responses…