Skip to search formSkip to main contentSkip to account menu
Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering
TLDR
A novel method of dynamically fuse multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities is proposed, which can robustly capture the high-level interactions between language and vision domains.
View on IEEE
Fast Convergence of DETR with Spatially Modulated Co-Attention
TLDR
This work proposes a simple yet effective scheme for improving the DETR framework, namely Spatially Modulated Co-Attention (SMCA) mechanism, which increases DETR’s convergence speed by replacing the original co-attention mechanism in the decoder while keeping other operations in DETR unchanged.
View on IEEE
CLIP-Adapter: Better Vision-Language Models with Feature Adapters
TLDR
This paper shows that there is an alternative path to achieve better vision-language models other than prompt tuning, and proposes CLIP-Adapter to conduct fine-tuning with feature adapters on either visual or language branch.
View PDF on arXiv
End-to-End Object Detection with Adaptive Clustering Transformer
TLDR
A novel variant of transformer named Adaptive Clustering Transformer named ACT has been proposed to reduce the computation cost for high-resolution input and achieves a good balance between accuracy and computation cost (FLOPs).
View PDF on arXiv
Multi-Modality Latent Interaction Network for Visual Question Answering
TLDR
The proposed Multi- modality Latent Interaction module (MLI) learns the cross-modality relationships between latent visual and language summarizations, which summarize visual regions and question into a small number of latent representations to avoid modeling uninformative individual region-word relations.
View on IEEE
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
TLDR
This work proposes a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format, and adopts it for various vision tasks from image to video domain, from classification to dense prediction.
View PDF on arXiv
Learning Where to Focus for Efficient Video Object Detection
TLDR
A novel module called Learnable Spatio-Temporal Sampling (LSTS) has been proposed to learn semantic-level correspondences among adjacent frame features accurately and achieves state-of-the-art performance on the ImageNet VID dataset with less computational complexity and real-time speed.
View via Publisher
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
TLDR
A novel Unified transFormer (UniFormer) which seamlessly integrates merits of 3D convolution and spatiotemporal self-attention in a concise transformer format, and achieves a preferable balance between computation and accuracy.
View PDF on arXiv
DNA-Net: Age and Gender Aware Kin Face Synthesizer
  • Peng Gao, Siyu Xia, Y. Fu
  • Computer Science
    IEEE International Conference on Multimedia and…
  • 16 November 2019
TLDR
This paper proposes a two-stage kin-face generation model to predict the appearance of a child given a pair of parents, and demonstrates the effectiveness of the proposed method quantitatively and qualitatively.
View on IEEE
Video Object Detection with Locally-Weighted Deformable Neighbors
TLDR
This paper proposes LWDN (Locally-Weighted Deformable Neighbors) for video object detection without utilizing time-consuming optical flow extraction networks and adopts brain-inspired memory mechanism to propagate and update the memory feature from keyframes to keyframes, called Memory-Guided Propagation.
View via Publisher
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License