StoMPP progressively binarizes BNN layers layerwise from input to output via stochastic masks, delivering depth-scalable accuracy gains in a fully STE-free regime by controlling activation-induced gradient blockades.
hub Canonical reference
In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Canonical reference. 100% of citing Pith papers cite this work as background.
18
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
An event-camera system with active gaze control and contrast-maximization spin estimation achieves real-time performance in table tennis with 8.8% magnitude error, 6.4° axis error, 3 ms latency, and 750 Hz throughput.
TIDES simulates realistic event camera streams in continuous time via dynamic Gaussian splatting with adaptive occlusion handling and sensor artifact modeling, claiming SOTA fidelity and better downstream transfer than prior methods.
HL-OutPaint enables high-resolution outpainting of long video sequences via a coarse-to-fine pipeline that first builds Global Coarse Guidance through global-local frame swapping then synthesizes details.
CEA assembles per-token low-rank residual updates via dense affinities over hyper-adapter-generated components to improve all-in-one image restoration on spatially non-uniform degradations.
DPQuant uses epoch-wise probabilistic layer rotation and DP loss sensitivity to quantize only a changing subset of layers, reducing accuracy degradation from quantization noise in DP-SGD and delivering up to 2.21x throughput gains with under 2% accuracy drop.
BEVCALIB performs LiDAR-camera calibration from raw data by fusing camera and LiDAR bird's-eye view features with a novel feature selector and reports state-of-the-art accuracy on KITTI and NuScenes.
Presents the ev-CIVIL dataset and benchmark showing that event-based cameras can support real-time detection of cracks and spalling in civil infrastructure under challenging lighting.
A co-design framework using approximate matrix decomposition and genetic algorithms delivers 33% average latency reduction in TinyML CNN FPGA accelerators with 1.3% average accuracy loss versus standard systolic arrays.
OxEnsemble improves fairness-accuracy trade-offs in low-data medical imaging by training fairness-constrained ensemble members and aggregating predictions with theoretical guarantees.
FSDC-DETR improves small-object AP by 6.8–6.9 points on VisDrone and AITODv2 by explicit frequency-spatial fusion and wavelet-style downsampling inside a DETR hybrid encoder.
Introduces LUMINA-26 low-light action dataset and Illumi-Net model achieving 75.95% Top-1 accuracy on it while surpassing prior SOTA on ELLAR.
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.
TMVA4D uses CNN and ConvLSTM encoders on multi-view 2D projections of 4D radar point clouds for semantic segmentation of people, reporting Dice 75.9% and IoU 61.2% in field tests.
SNNs deployed on Loihi 2 achieve real-time object detection with the lowest dynamic energy per inference and recover 87-100% of ANN accuracy via distillation-aware training.
Presents a non-distortive cancelable face template method via targeted image distortion that maintains identity signals for neural embedding models on MNIST and LFW data.
The SoccerNet 2026 Challenges benchmarked 427 teams across five soccer video understanding tasks, with leading submissions improving over baselines on all tasks.
A literature review that categorizes deep learning approaches for visual hand gesture recognition, summarizes state-of-the-art methods across tasks, reviews datasets and metrics, and identifies challenges and future directions.
citing papers explorer
-
Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks
StoMPP progressively binarizes BNN layers layerwise from input to output via stochastic masks, delivering depth-scalable accuracy gains in a fully STE-free regime by controlling activation-induced gradient blockades.
-
Event-based Gaze Control System for Accurate Real-time Spin Estimation in Professional Ball Games
An event-camera system with active gaze control and contrast-maximization spin estimation achieves real-time performance in table tennis with 8.8% magnitude error, 6.4° axis error, 3 ms latency, and 750 Hz throughput.
-
TIDES: Time-Derivative Event Simulation via Deformable Reconstruction
TIDES simulates realistic event camera streams in continuous time via dynamic Gaussian splatting with adaptive occlusion handling and sensor artifact modeling, claiming SOTA fidelity and better downstream transfer than prior methods.
-
HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos
HL-OutPaint enables high-resolution outpainting of long video sequences via a coarse-to-fine pipeline that first builds Global Coarse Guidance through global-local frame swapping then synthesizes details.
-
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
CEA assembles per-token low-rank residual updates via dense affinities over hyper-adapter-generated components to improve all-in-one image restoration on spatially non-uniform degradations.
-
DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
DPQuant uses epoch-wise probabilistic layer rotation and DP loss sensitivity to quantize only a changing subset of layers, reducing accuracy degradation from quantization noise in DP-SGD and delivering up to 2.21x throughput gains with under 2% accuracy drop.
-
BEVCALIB: LiDAR-Camera Calibration via Geometry-Guided Bird's-Eye View Representations
BEVCALIB performs LiDAR-camera calibration from raw data by fusing camera and LiDAR bird's-eye view features with a novel feature selector and reports state-of-the-art accuracy on KITTI and NuScenes.
-
Event-based Civil Infrastructure Visual Defect Detection: ev-CIVIL Dataset and Benchmark
Presents the ev-CIVIL dataset and benchmark showing that event-based cameras can support real-time detection of cracks and spalling in civil infrastructure under challenging lighting.
-
Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition
A co-design framework using approximate matrix decomposition and genetic algorithms delivers 33% average latency reduction in TinyML CNN FPGA accelerators with 1.3% average accuracy loss versus standard systolic arrays.
-
OxEnsemble: Fair Ensembles for Low-Data Classification
OxEnsemble improves fairness-accuracy trade-offs in low-data medical imaging by training fairness-constrained ensemble members and aggregating predictions with theoretical guarantees.
-
FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection
FSDC-DETR improves small-object AP by 6.8–6.9 points on VisDrone and AITODv2 by explicit frequency-spatial fusion and wavelet-style downsampling inside a DETR hybrid encoder.
-
LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions
Introduces LUMINA-26 low-light action dataset and Illumi-Net model achieving 75.95% Top-1 accuracy on it while surpassing prior SOTA on ELLAR.
-
Out-of-Distribution Generalization in Time Series: A Survey
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.
-
4D Radar Semantic Segmentation of People in Field Conditions Using Temporal Multi-View Networks
TMVA4D uses CNN and ConvLSTM encoders on multi-view 2D projections of 4D radar point clouds for semantic segmentation of people, reporting Dice 75.9% and IoU 61.2% in field tests.
-
Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark
SNNs deployed on Loihi 2 achieve real-time object detection with the lowest dynamic energy per inference and recover 87-100% of ANN accuracy via distillation-aware training.
-
Embedding Non-Distortive Cancelable Face Template Generation
Presents a non-distortive cancelable face template method via targeted image distortion that maintains identity signals for neural embedding models on MNIST and LFW data.
-
SoccerNet 2026 Challenges Results
The SoccerNet 2026 Challenges benchmarked 427 teams across five soccer video understanding tasks, with leading submissions improving over baselines on all tasks.
-
Visual Hand Gesture Recognition with Deep Learning: A Comprehensive Review of Methods, Datasets, Challenges and Future Research Directions
A literature review that categorizes deep learning approaches for visual hand gesture recognition, summarizes state-of-the-art methods across tasks, reviews datasets and metrics, and identifies challenges and future directions.