Tongji University

About: Tongji University is a education organization based out in Shanghai, China. It is known for research contribution in the topics: Computer science & Population. The organization has 76116 authors who have published 81176 publications receiving 1248911 citations. The organization is also known as: Tongji & Tóngjì Dàxué.

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

Abstract: We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of image feature map of size H × W. In our method, however, a fixed sparse set of learned object proposals, total length of N, are provided to object recognition head to perform classification and location. By eliminating HWk (up to hundreds of thousands) hand-designed object candidates to N (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-to-one label assignment. More importantly, final predictions are directly output without non-maximum suppression post-procedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the well-established detector baselines on the challenging COCO dataset, e.g., achieving 45.0 AP in standard 3× training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN.

Real-Time Action Recognition with Enhanced Motion Vector CNNs

Abstract: The deep two-stream architecture [23] exhibited excellent performance on video based action recognition. The most computationally expensive step in this approach comes from the calculation of optical flow which prevents it to be real-time. This paper accelerates this architecture by replacing optical flow with motion vector which can be obtained directly from compressed videos without extra calculation. However, motion vector lacks fine structures, and contains noisy and inaccurate motion patterns, leading to the evident degradation of recognition performance. Our key insight for relieving this problem is that optical flow and motion vector are inherent correlated. Transferring the knowledge learned with optical flow CNN to motion vector CNN can significantly boost the performance of the latter. Specifically, we introduce three strategies for this, initialization transfer, supervision transfer and their combination. Experimental results show that our method achieves comparable recognition performance to the state-of-the-art, while our method can process 390.7 frames per second, which is 27 times faster than the original two-stream method.

Impact of Specific Epidermal Growth Factor Receptor (EGFR) Mutations and Clinical Characteristics on Outcomes After Treatment With EGFR Tyrosine Kinase Inhibitors Versus Chemotherapy in EGFR-Mutant Lung Cancer: A Meta-Analysis

Abstract: Purpose We examined the impact of different epidermal growth factor receptor (EGFR) mutations and clinical characteristics on progression-free survival (PFS) in patients with advanced EGFR-mutated non–small-cell lung cancer treated with EGFR tyrosine kinase inhibitors (TKIs) as first-line therapy. Patients and Methods This meta-analysis included randomized trials comparing EGFR TKIs with chemotherapy. We calculated hazard ratios (HRs) and 95% CIs for PFS for the trial population and prespecified subgroups and calculated pooled estimates of treatment efficacy using the fixed-effects inverse-variance-weighted method. All statistical tests were two sided. Results In seven eligible trials (1,649 patients), EGFR TKIs, compared with chemotherapy, significantly prolonged PFS overall (HR, 0.37; 95% CI, 0.32 to 0.42) and in all subgroups. For tumors with exon 19 deletions, the benefit was 50% greater (HR, 0.24; 95% CI, 0.20 to 0.29) than for tumors with exon 21 L858R substitution (HR, 0.48; 95% CI, 0.39 to 0.58; P...