Search Results for author:
Found 8 papers, 2 papers with code
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
Our approach not only enhances computational efficiency but also aligns naturally with image generation principles by operating in continuous token space and following a hierarchical generation process from coarse to fine details.
DiTFastAttn: Attention Compression for Diffusion Transformer Models
Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators.
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations.
Ranked #2 on
Unsupervised Semantic Segmentation
on COCO-Stuff-171
(using extra training data)
Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild
This paper proposes a framework for the interactive video object segmentation (VOS) in the wild where users can choose some frames for annotations iteratively.
Deep Reinforcement Learning
Interactive Video Object Segmentation
A novel graph structure for salient object detection based on divergence background and compact foreground
Different from prior methods, we calculate the saliency value of each node based on the relationship between the corresponding node and the virtual node.
Saliency detection by aggregating complementary background template with optimization framework
This paper proposes an unsupervised bottom-up saliency detection approach by aggregating complementary background template with refinement.
Saliency Detection combining Multi-layer Integration algorithm with background prior and energy function
In this paper, we propose an improved mechanism for saliency detection.
Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation
These parts are referred to as Frequent Local Parts or FLPs.
