Search Results - Proceedings of the IEEE/CVF Conference on Computer Vision AND Pattern Recognition

Subspace-PnP: A Geometric Constraint Loss for Mutual Assistance of Depth and Optical Flow Estimation by Chi, Cheng, Hao, Tianyu, Wang, Qingjie, Guo, Peng, Yang, Xin

“…, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4654–4665, 2020; Ranjan et al., in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12240…”
Get full text

Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio- Visual Event Perception by Gao, Junyu, Chen, Mengyuan, Xu, Changsheng

“…With only video-level event labels, this paper targets at the task of weakly-supervised audio-visual event perception (WS-AVEP), which aims to temporally…”
Get full text

Bottleneck Transformers for Visual Recognition by Srinivas, Aravind, Lin, Tsung-Yi, Parmar, Niki, Shlens, Jonathon, Abbeel, Pieter, Vaswani, Ashish

“… By just replacing the spatial convolutions with global self-attention in the final three bottleneck blocks of a ResNet and no other changes, our approach improves upon the baselines significantly on…”
Get full text

Masked-attention Mask Transformer for Universal Image Segmentation by Cheng, Bowen, Misra, Ishan, Schwing, Alexander G., Kirillov, Alexander, Girdhar, Rohit

“… Each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing spe-cialized architectures for each task…”
Get full text

GLIGEN: Open-Set Grounded Text-to-Image Generation by Li, Yuheng, Liu, Haotian, Wu, Qingyang, Mu, Fangzhou, Yang, Jianwei, Gao, Jianfeng, Li, Chunyuan, Lee, Yong Jae

“… enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism…”
Get full text

Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection by Haliassos, Alexandros, Vougioukas, Konstantinos, Petridis, Stavros, Pantic, Maja

“…), thus learning rich internal representations related to natural mouth motion. A temporal network is subsequently finetuned on fixed mouth embeddings of real and…”
Get full text

Deformable ConvNets V2: More Deformable, Better Results by Zhu, Xizhou, Hu, Han, Lin, Stephen, Dai, Jifeng

“…The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects…”
Get full text

Google Landmarks Dataset v2 - A Large-Scale Benchmark for Instance-Level Recognition and Retrieval by Weyand, Tobias, Araujo, Andre, Cao, Bingyi, Sim, Jack

“…), a new benchmark for large-scale, fine-grained instance recognition and image retrieval in the domain of human-made and natural landmarks…”
Get full text

Dense Contrastive Learning for Self-Supervised Visual Pre-Training by Wang, Xinlong, Zhang, Rufeng, Shen, Chunhua, Kong, Tao, Li, Lei

“… To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features…”
Get full text

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks by Dong, Yinpeng, Pang, Tianyu, Su, Hang, Zhu, Jun

“… Due to the threat of adversarial attacks, many methods have been proposed to improve the robustness…”
Get full text

Deformable Siamese Attention Networks for Visual Object Tracking by Yu, Yuechen, Xiong, Yilei, Huang, Weilin, Scott, Matthew R.

“… However, the target template is not updated online, and the features of target template and search image are computed independently in a Siamese architecture…”
Get full text

MobileOne: An Improved One millisecond Mobile Backbone by Vasu, Pavan Kumar Anasosalu, Gabriel, James, Zhu, Jeff, Tuzel, Oncel, Ranjan, Anurag

“… However, these metrics may not correlate well with latency of the network when deployed on a mobile device…”
Get full text

Multi-class Token Transformer for Weakly Supervised Semantic Segmentation by Xu, Lian, Ouyang, Wanli, Bennamoun, Mohammed, Boussaid, Farid, Xu, Dan

“…). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer…”
Get full text

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation by Zhang, Wenqiang, Huang, Zilong, Luo, Guozhong, Chen, Tao, Wang, Xinggang, Liu, Wenyu, Yu, Gang, Shen, Chunhua

“…Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices…”
Get full text

Causality Inspired Representation Learning for Domain Generalization by Lv, Fangrui, Liang, Jian, Li, Shuang, Zang, Bin, Liu, Chi Harold, Wang, Ziteng, Liu, Di

“…Domain generalization (DG) is essentially an out-of-distribution problem, aiming to generalize the knowledge learned from multiple source domains to an unseen target domain…”
Get full text

Deep Snake for Real-Time Instance Segmentation by Peng, Sida, Jiang, Wen, Pi, Huaijin, Li, Xiuli, Bao, Hujun, Zhou, Xiaowei

“… For structured feature learning on the contour, we propose to use circular convolution in deep snake, which better exploits the cycle-graph structure of a contour compared against generic graph convolution…”
Get full text

Token Contrast for Weakly-Supervised Semantic Segmentation by Ru, Lixiang, Zheng, Heliang, Zhan, Yibing, Du, Bo

“…) to generate the pseudo labels. Limited by the local structure perception of CNN, CAM usually cannot identify the integral object regions…”
Get full text

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal by Li, Hongyang, Eigen, David, Dodge, Samuel, Zeiler, Matthew, Wang, Xiaogang

“… Because of this, they are constrained to use a single set of features for all possible test-time tasks, which hinders the ability to distinguish the most relevant dimensions for the task at hand…”
Get full text

Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction by Ma, Tiezheng, Nie, Yongwei, Long, Chengjiang, Zhang, Qing, Li, Guiqing

“… Our method is based on the observation that a good "initial guess" of the future poses is very helpful in improving the forecasting accuracy…”
Get full text

Wavelet Integrated CNNs for Noise-Robust Image Classification by Li, Qiufu, Shen, Linlin, Guo, Sheng, Lai, Zhihui

“… The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets…”
Get full text