Unified 3d segmenter as prototypical classifiers
The task of point cloud segmentation, comprising semantic, instance, and panoptic
segmentation, has been mainly tackled by designing task-specific network architectures …
segmentation, has been mainly tackled by designing task-specific network architectures …
Local-global context aware transformer for language-guided video segmentation
We explore the task of language-guided video segmentation (LVS). Previous algorithms
mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context …
mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context …
[PDF][PDF] Prompt Learns Prompt: Exploring Knowledge-Aware Generative Prompt Collaboration For Video Captioning.
Fine-tuning large vision-language models is a challenging task. Prompt tuning approaches
have been introduced to learn fixed textual or visual prompts while freezing the pre-trained …
have been introduced to learn fixed textual or visual prompts while freezing the pre-trained …
Unified mask embedding and correspondence learning for self-supervised video segmentation
The objective of this paper is self-supervised learning of video object segmentation. We
develop a unified framework which simultaneously models cross-frame dense …
develop a unified framework which simultaneously models cross-frame dense …
Promotion: Prototypes as motion learners
In this work we introduce ProMotion a unified prototypical transformer-based framework
engineered to model fundamental motion tasks. ProMotion offers a range of compelling …
engineered to model fundamental motion tasks. ProMotion offers a range of compelling …
Clip fusion with bi-level optimization for human mesh reconstruction from monocular videos
Human mesh reconstruction (HMR) from monocular video is the key step to many mixed
reality and robotic applications. Although existing methods show promising results by …
reality and robotic applications. Although existing methods show promising results by …
Dual-constraint coarse-to-fine network for camouflaged object detection
Camouflaged object detection (COD) is an important yet challenging task, with great
application values in industrial defect detection, medical care, etc. The challenges mainly …
application values in industrial defect detection, medical care, etc. The challenges mainly …
Video corpus moment retrieval via deformable multigranularity feature fusion and adversarial training
As a new emerging task, video corpus moment retrieval (VCMR) aims to find the video
segments relevant to a given natural language query from a large number of untrimmed …
segments relevant to a given natural language query from a large number of untrimmed …
Image translation as diffusion visual programmers
We introduce the novel Diffusion Visual Programmer (DVP), a neuro-symbolic image
translation framework. Our proposed DVP seamlessly embeds a condition-flexible diffusion …
translation framework. Our proposed DVP seamlessly embeds a condition-flexible diffusion …
Hybridvps: Hybrid-supervised video polyp segmentation under low-cost labels
Deep polyp segmentation methods have shown remarkable potential in boosting diagnostic
efficiency. Nevertheless, these methods rely on sufficient pixel-wise annotated data, which is …
efficiency. Nevertheless, these methods rely on sufficient pixel-wise annotated data, which is …