{"total":14,"items":[{"citing_arxiv_id":"2606.09881","ref_index":99,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","primary_cat":"cs.LG","submitted_at":"2026-06-03T05:44:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20445","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Comprehensive Comparison of Deep Learning Architectures for COVID-19 Classification on CT & X-ray Imagery","primary_cat":"cs.CV","submitted_at":"2026-05-19T19:57:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"ResNet and VGG models achieve 95-98% average accuracy distinguishing COVID-19 from normal lung images on X-ray and CT datasets using transfer learning from pre-trained networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24426","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DYMAPIA: A Multi-Domain Framework for Detecting AI-based Video Manipulation","primary_cat":"cs.CV","submitted_at":"2026-04-27T12:53:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"DYMAPIA builds dynamic anomaly masks from Fourier spectra, texture, edges, and optical flow to guide a lightweight DistXCNet classifier, reporting over 99% accuracy and F1 on FF++, Celeb-DF, and VDFD.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14570","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Deepfake Detection Generalization with Diffusion Noise","primary_cat":"cs.CV","submitted_at":"2026-04-16T03:02:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ANL uses diffusion noise prediction and attention to regularize deepfake detectors for better generalization to unseen synthesis methods without added inference cost.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[7] Jongwook Choi, Taehoon Kim, Yonghyun Jeong, Seungryul Baek, and Jongwon Choi. 2024. Exploiting Style Latent Flows for Generalizing Deepfake Video Detection. arXiv:2403.06592 [cs.CV] https://arxiv.org/abs/2403.06592 [8] François Chollet. 2017. Xception: Deep Learning with Depthwise Separable Convolutions. arXiv:1610.02357 [cs.CV] https://arxiv.org/abs/1610.02357 [9] Hyungjin Chung and Jong Chul Ye. 2022. Score-based diffusion models for accelerated MRI. arXiv:2110.05243 [eess.IV] https://arxiv.org/abs/2110.05243 [10] Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, and Luisa Verdoliva. 2022. On the detection of synthetic images generated by diffusion models. arXiv:2211.00680 [cs."},{"citing_arxiv_id":"2602.15946","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On-chip probabilistic inference for charged-particle tracking at the sensor edge","primary_cat":"physics.ins-det","submitted_at":"2026-02-17T19:03:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Neural networks integrated into silicon sensor front-end electronics can regress charged-particle hit positions and angles with calibrated uncertainties from single-layer data while satisfying hardware constraints on precision, latency, and area.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.06876","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Separable Convolutional LSTMs for Faster Video Segmentation","primary_cat":"cs.CV","submitted_at":"2019-07-16T07:52:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Separable convLSTMs cut parameters and FLOPs in video segmentation, delivering up to 15% faster GPU inference with similar or slightly lower accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.06291","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Measuring the Transferability of Adversarial Examples","primary_cat":"cs.LG","submitted_at":"2019-07-14T22:20:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Empirical measurement of adversarial example transferability between VGG and Inception model classes with methodological refinements to attack strength selection, perturbation clipping, and evaluation via SSIM.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.04648","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"EPNAS: Efficient Progressive Neural Architecture Search","primary_cat":"cs.LG","submitted_at":"2019-07-07T03:50:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.01342","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation","primary_cat":"cs.CV","submitted_at":"2019-07-02T13:17:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Defining egoistic and altruistic cost functions for class confusions in semantic segmentation changes precision, recall, and segment-wise error rates relative to standard MAP decisions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.10104","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Remote Estimation of Free-Flow Speeds","primary_cat":"cs.CV","submitted_at":"2019-06-24T17:41:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A CNN estimates free-flow speeds from aerial imagery and metadata, performing nearly as well with imagery alone as with road features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.09433","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Deep Single Image Deraining Via Estimating Transmission and Atmospheric Light in rainy Scenes","primary_cat":"cs.CV","submitted_at":"2019-06-22T10:58:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A deep network estimates per-image atmospheric light and a transmission map, then recovers a clear image from the atmospheric scattering model, outperforming prior deraining methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1706.05587","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","primary_cat":"cs.CV","submitted_at":"2017-06-17T22:48:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DeepLabv3 improves semantic segmentation by capturing multi-scale context with cascaded or parallel atrous convolutions and adding global context to ASPP, achieving better results on PASCAL VOC 2012 without DenseCRF post-processing.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"[11] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. arXiv:1606.00915, 2016. [12] L.-C. Chen, Y . Yang, J. Wang, W. Xu, and A. L. Yuille. At- tention to scale: Scale-aware semantic image segmentation. In CVPR, 2016. [13] F. Chollet. Xception: Deep learning with depthwise separable convolutions. arXiv:1610.02357, 2016. Figure 8. Visualization results on Cityscapes val set when training with only train fine set. [14] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele. The cityscapes dataset for semantic urban scene understanding."},{"citing_arxiv_id":"1706.03762","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Attention Is All You Need","primary_cat":"cs.CL","submitted_at":"2017-06-12T17:57:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"UNKNOWN","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Pith review generated a malformed one-line summary.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"positions. Doing so requires a stack ofO(n/k) convolutional layers in the case of contiguous kernels, orO(logk(n)) in the case of dilated convolutions [ 18], increasing the length of the longest paths between any two positions in the network. Convolutional layers are generally more expensive than recurrent layers, by a factor of k. Separable convolutions [ 6], however, decrease the complexity considerably, toO(k·n·d +n·d2). Even with k = n, however, the complexity of a separable convolution is equal to the combination of a self-attention layer and a point-wise feed-forward layer, the approach we take in our model. As side benefit, self-attention could yield more interpretable models. We inspect attention distributions"},{"citing_arxiv_id":"1704.04861","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","primary_cat":"cs.CV","submitted_at":"2017-04-17T03:57:34+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MobileNets introduce depthwise separable convolutions plus width and resolution multipliers to produce efficient CNNs that trade off latency and accuracy for mobile and embedded vision applications.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"used in Inception models [13] to reduce the computation in the first few layers. Flattened networks [16] build a network out of fully factorized convolutions and showed the poten- tial of extremely factorized networks. Independent of this current paper, Factorized Networks[34] introduces a similar factorized convolution as well as the use of topological con- nections. Subsequently, the Xception network [3] demon- strated how to scale up depthwise separable filters to out perform Inception V3 networks. Another small network is Squeezenet [12] which uses a bottleneck approach to design a very small network. Other reduced computation networks include structured transform networks [28] and deep fried convnets [37]. A different approach for obtaining small networks is"}],"limit":50,"offset":0}