Related papers: TokenMotion: Motion-Guided Vision Transformer for …
Recent developments in Transformers have achieved notable strides in enhancing video comprehension. Nonetheless, the O($N^2$) computation complexity associated with attention mechanisms presents substantial computational hurdles when…
Camouflaged Object Detection (COD) is challenging due to the strong similarity between camouflaged objects and their surroundings, which complicates identification. Existing methods mainly rely on spatial local features, failing to capture…
Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods typically use convolutional neural networks (CNNs) to predict motion information, such as motion keypoints and…
Text-Video retrieval is a task of great practical value and has received increasing attention, among which learning spatial-temporal video representation is one of the research hotspots. The video encoders in the state-of-the-art video…
In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting…
Many existing motion prediction approaches rely on symbolic perception outputs to generate agent trajectories, such as bounding boxes, road graph information and traffic lights. This symbolic representation is a high-level abstraction of…
Camouflaged object detection (COD) aims to segment objects visually embedded in their surroundings, which is a very challenging task due to the high similarity between the objects and the background. To address it, most methods often…
Convolutional Neural networks (CNN) have been the first choice of paradigm in many computer vision applications. The convolution operation however has a significant weakness which is it only operates on a local neighborhood of pixels, thus…
Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…
Camouflaged object detection (COD) aims to segment objects that blend into their surroundings. However, most existing studies overlook the semantic differences among textual prompts of different targets as well as fine-grained frequency…
Moving Object Detection (MOD) is a fundamental step for many computer vision applications. MOD becomes very challenging when a video sequence captured from a static or moving camera suffers from the challenges: camouflage, shadow, dynamic…
Video Camouflaged Object Detection (VCOD) is currently constrained by the scarcity of challenging benchmarks and the limited robustness of models against erratic motion dynamics. Existing methods often struggle with Motion-Induced…
Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled source domain to an unlabeled target domain. Despite recent advances, existing VUDA methods…
Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods primarily employ semantic segmentation, which suffers from…
Weakly supervised multimodal video anomaly detection has gained significant attention, yet the potential of the text modality remains under-explored. Text provides explicit semantic information that can enhance anomaly characterization and…
Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…
Vision transformers have recently shown strong global context modeling capabilities in camouflaged object detection. However, they suffer from two major limitations: less effective locality modeling and insufficient feature aggregation in…
This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. The essential…
Camouflaged object detection (COD), which aims to identify the objects that conceal themselves into the surroundings, has recently drawn increasing research efforts in the field of computer vision. In practice, the success of deep learning…
Camouflaged object detection (COD) and salient object detection (SOD) are two distinct yet closely-related computer vision tasks widely studied during the past decades. Though sharing the same purpose of segmenting an image into binary…