A linearized solver estimates rolling-shutter relative pose and motion from 7 affine correspondences in 1.2 ms and reports best-in-benchmark accuracy plus usable translational velocity.
Canonical reference
Title resolution pending
Canonical reference. 82% of citing Pith papers cite this work as background.
54
Pith papers citing it
Background
82% of classified citations
citation-role summary
background 8
dataset 2
baseline 1
citation-polarity summary
representative citing papers
A self-supervised method pretrains an encoder on eight PSP images per view to learn generalizable subsurface scattering representations that transfer to relighting and dense footprint reconstruction on unseen complex objects.
The paper defines the 4DVLT task for worldline-centered 4D scene understanding, releases Instruct-4D with 129.4K QA pairs, and presents 4DTrack achieving 62.68 TGA_Top1, outperforming adapted baselines by 19.62 points.
WHU-Infra3D is a new large-scale multi-modal dataset and benchmark for 3D roadside infrastructure inventory, providing over 175k 2D boxes, thousands of 3D instances, and 181k annotations across five core tasks while exposing cross-city gaps and long-tailed defect vulnerabilities.
On the public ReMIND dataset, a systematic benchmark of six synthesis models across 48 experiments finds LPIPS correlates with downstream segmentation utility while SSIM does not, with SynDiff-2.5D performing best.
Urban-ImageNet is a 2-million-image multi-modal dataset with HUSIC 10-class taxonomy enabling benchmarks for urban scene classification, cross-modal retrieval, and instance segmentation.
Gaussian Kernel Attention replaces learned QKV projections with a Gaussian RBF kernel on per-head token features, using 0.42x parameters and 0.49x FLOPs while showing competitive language modeling performance at depth 20.
DP-GCL improves differentially private contrastive learning by bounding group-level contributions through batch partitioning and intra-group augmentation, delivering 5.6% higher image classification accuracy and 20.1% higher retrieval accuracy than existing approaches.
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
A system combining VLM landmark instructions with real-time corrective spatial audio reduces route deviations in a small user study compared to VLM-only and Google Maps audio baselines.
MobileMold provides 4941 smartphone microscopy images and shows deep learning models reach 99.5% accuracy on mold detection and food classification tasks.
Quantum circuits for coherent multilayer neural network inference achieve quadratic to polylogarithmic speedups over classical methods depending on quantum data access models for inputs and weights.
MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.
AF3AD is a modular synthesis framework using center-conditioned parametric deformations in local PCA frames to create diverse pseudo-anomalies, improving unsupervised 3D anomaly detection on AnomalyShapeNet and Real3D-AD.
LAFM adapts the source distribution in flow matching policies via a latent action model to better match fragmented robotic action spaces, claiming 23.4% higher real-world success and 10.4% on LIBERO-90 while beating larger pre-trained models.
RBFN projection heads serve as competitive replacements for MLP heads in SSL and enable SNS, a label-free metric from RBF parameters that correlates strongly with logistic regression evaluation.
FATE combines pillar encoding via orthogonal polynomial basis with frequency-aware training to enable event-based object detection at up to 200 Hz without internal temporal sub-binning.
Jaguar replaces prime-modulus HE with power-of-two arithmetic to enable coefficient-domain convolution and local-shift truncation, reporting 2-3.7x lower latency than Cheetah and Rhombus on ResNet-18/50 and MobileNetV2.
Tetris decomposes stationary videos into tile polyominoes and applies classifier plus ILP pruning to cut detector calls, staying within 5% accuracy loss while delivering up to 17.4x throughput gains over priors.
New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
Neighbor2Inverse adapts the Neighbor2Neighbor principle to train a denoising network directly in the image domain for low-dose PBI-CT by using independently noised subsampled projections.
Remote SAMsing pipeline boosts SAM2 coverage on remote sensing scenes from 30-68% to 91-98% via multi-pass masking and boundary-aware merging while preserving mask quality.
A threat-oriented digital twinning methodology and open-source modular twin is introduced for security evaluation of autonomous platforms, translating threat analysis into controllable tests for spoofing, replay, and adversarial ML attacks.
citing papers explorer
-
Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks
Introduces Explicit Logic Channel (ELC) with LLM, VFM and probabilistic inference for validating, selecting and enhancing MLLMs on zero-shot tasks using Consistency Rate and cross-channel integration.
-
A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting
A learned linear activation bridge achieves high alignment (cosine ~0.97) between Pythia-160M and Pythia-410M states but produces no improvement in downstream multi-hop answering when injected into the receiver.