MoCapAnything V2 presents the first end-to-end learnable Video-to-Pose and Pose-to-Rotation framework for monocular arbitrary-skeleton motion capture by conditioning on a reference pose-rotation pair.
super hub Mixed citations
A ConvNet for the 2020s
Mixed citation behavior. Most common role is background (66%).
307
Pith papers citing it
725
external citations · external index
Background
66% of classified citations
hub tools
citation-role summary
background 43
method 9
baseline 6
dataset 6
citation-polarity summary
authors
co-cited works
representative citing papers
Neural simulation-based inference on unbinned top-quark pair data at 13 TeV yields improved gluon PDF precision over traditional binned analyses while incorporating experimental and theoretical uncertainties.
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
SCOREBED isolates EIG double intractability in a policy-independent score-matching stage, then trains design policies with a singly intractable gradient estimator, enabling cheap multi-policy selection.
SPoILeR uses multimodal pre-training to enable accurate novel view synthesis of infrared, polarimetric, and multispectral data from RGB-supervised fine-tuning on new scenes.
AbsoluteDegradation supplies a physics-inspired synthetic degradation pipeline and a large real-world archival benchmark to train and evaluate film restoration models.
MoHallBench is a new benchmark evaluating motion hallucination in VideoLLMs from co-occurrence priors, sequential inference, and similarity confusion, revealing decoupling from action recognition performance.
GenTUS reformulates table union search as constrained generative retrieval over semantic table identifiers, achieving top retrieval quality on seven benchmarks with lower latency and storage costs.
PRISM-VO introduces photometric plenoptic bundle adjustment for drift-resilient, metric-scale visual odometry from a single focused plenoptic camera.
SpheRoPE modifies rotary position embeddings in diffusion transformers to enforce spherical topology for zero-shot 360 panorama generation across multiple backbones.
RESOLVE provides a controlled multi-resolution LiDAR and camera benchmark for evaluating 3D detection and tracking under point sparsity variations in roadside cooperative perception.
Q-Margin encodes margin penalties into the reference measure of an alpha-divergence loss to produce sparse discriminative embeddings for face and speaker verification.
MLLMs drop from over 85% accuracy on action presence to under 50% on matched action-denial videos, exposing a causal verification gap that causal graph prompts partially close.
A regularization technique that treats diffusion model outputs as a similarity kernel during material optimization in inverse rendering, enabling joint reconstruction of geometry, materials, and illumination that satisfies the rendering equation and generalizes to new lighting.
HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.
Miti360 is a new annotated aerial and terrestrial imagery dataset from a Kenyan reforestation site that supports ML models for tree detection, species mapping, and growth modeling in Africa.
Neural swipe decoder trained with geometric augmentations on 1M+ swipes generalizes to unseen keyboard layouts by predicting per-point character locations and mapping via inference-time layout.
MATCH is the first flow matching method for multi-view anomaly detection, reporting SOTA results on Real-IAD and the first comprehensive evaluation on MANTA-Tiny while enabling real-time use by omitting the divergence term.
A technique for controllable diversity in text-to-image generation by inducing structured semantic variations at the prompt level via VLM and agentic workflow.
GeoFidelity-Bench shows text-to-image models gain city-level plausibility from local names but achieve near-zero improvement in exact segment identity, with GPS coordinates adding no benefit.
Arbor attaches constraint mesh tokens to a frozen text-to-3D denoiser to enable controllable generation obeying hull, avoidance, and touch constraints.
FlowPaint reframes censorship evasion as semantic image-to-image editing with instruction-tuned diffusion models, claiming single-prompt robustness against both rule-based and ML-based censors.
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.
TIGER turns the low-rank attention gradient subspace into a differentiable objective for continuous embedding optimization, improving reconstruction quality and robustness over prior discrete token tests especially under noise or DP.
citing papers explorer
-
MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
MoCapAnything V2 presents the first end-to-end learnable Video-to-Pose and Pose-to-Rotation framework for monocular arbitrary-skeleton motion capture by conditioning on a reference pose-rotation pair.
-
Proton Structure from Neural Simulation-Based Inference at the LHC
Neural simulation-based inference on unbinned top-quark pair data at 13 TeV yields improved gluon PDF precision over traditional binned analyses while incorporating experimental and theoretical uncertainties.
-
A document is worth a structured record: Principled inductive bias design for document recognition
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
-
Bayesian Experimental Design via Score Matching
SCOREBED isolates EIG double intractability in a policy-independent score-matching stage, then trains design policies with a singly intractable gradient estimator, enabling cheap multi-policy selection.
-
Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis
SPoILeR uses multimodal pre-training to enable accurate novel view synthesis of infrared, polarimetric, and multispectral data from RGB-supervised fine-tuning on new scenes.
-
AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark
AbsoluteDegradation supplies a physics-inspired synthetic degradation pipeline and a large real-world archival benchmark to train and evaluate film restoration models.
-
MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models
MoHallBench is a new benchmark evaluating motion hallucination in VideoLLMs from co-occurrence priors, sequential inference, and similarity confusion, revealing decoupling from action recognition performance.
-
Generative Retrieval for Table Union Search
GenTUS reformulates table union search as constrained generative retrieval over semantic table identifiers, achieving top retrieval quality on seven benchmarks with lower latency and storage costs.
-
PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment
PRISM-VO introduces photometric plenoptic bundle adjustment for drift-resilient, metric-scale visual odometry from a single focused plenoptic camera.
-
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
SpheRoPE modifies rotary position embeddings in diffusion transformers to enforce spherical topology for zero-shot 360 panorama generation across multiple backbones.
-
RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception
RESOLVE provides a controlled multi-resolution LiDAR and camera benchmark for evaluating 3D detection and tracking under point sparsity variations in roadside cooperative perception.
-
Sparsity-Inducing Divergence Losses for Biometric Verification
Q-Margin encodes margin penalties into the reference measure of an alpha-divergence loss to produce sparse discriminative embeddings for face and speaker verification.
-
Learning to Deny: Action Denial in Multimodal Large Language Models
MLLMs drop from over 85% accuracy on action presence to under 50% on matched action-denial videos, exposing a causal verification gap that causal graph prompts partially close.
-
Diffusion-Based Material Regularization for Physics-Based Inverse Rendering
A regularization technique that treats diffusion model outputs as a similarity kernel during material optimization in inverse rendering, enabling joint reconstruction of geometry, materials, and illumination that satisfies the rendering equation and generalizes to new lighting.
-
HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks
HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.
-
Miti360: A Comprehensive Dataset for Improved Reforestation Monitoring
Miti360 is a new annotated aerial and terrestrial imagery dataset from a Kenyan reforestation site that supports ML models for tree detection, species mapping, and growth modeling in Africa.
-
FUTO Swipe: Layout-Agnostic Neural Swipe Decoding
Neural swipe decoder trained with geometric augmentations on 1M+ swipes generalizes to unseen keyboard layouts by predicting per-point character locations and mapping via inference-time layout.
-
MATCH: Flow Matching for Multi-View Anomaly Detection
MATCH is the first flow matching method for multi-view anomaly detection, reporting SOTA results on Real-IAD and the first comprehensive evaluation on MANTA-Tiny while enabling real-time use by omitting the divergence term.
-
Semantic Browsing: Controllable Diversity for Image Generation
A technique for controllable diversity in text-to-image generation by inducing structured semantic variations at the prompt level via VLM and agentic workflow.
-
GeoFidelity-Bench: Evaluating Segment-Level Geographic Fidelity in Text-to-Image Street-View Generation
GeoFidelity-Bench shows text-to-image models gain city-level plausibility from local names but achieve near-zero improvement in exact segment identity, with GPS coordinates adding no benefit.
-
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
Arbor attaches constraint mesh tokens to a frozen text-to-3D denoiser to enable controllable generation obeying hull, avoidance, and touch constraints.
-
One-Prompt Censorship Evasion via Generative Diffusion Models
FlowPaint reframes censorship evasion as semantic image-to-image editing with instruction-tuned diffusion models, claiming single-prompt robustness against both rule-based and ML-based censors.
-
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
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.
-
TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization
TIGER turns the low-rank attention gradient subspace into a differentiable objective for continuous embedding optimization, improving reconstruction quality and robustness over prior discrete token tests especially under noise or DP.
-
TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation
A two-stage generative model (Graph CVAE + flow matching) learns topology-agnostic motion codes from a new 5k-topology dataset and retargets video motion to arbitrary unseen skeletons.
-
Spectrally Regularized Latent Flow Matching for Turbulence Generation
Spectrally regularized compression in latent flow matching raises retained deep-dissipation spectral power from 20% to 79% in generated turbulence on a 256^2 DNS dataset at Re_f ≈ 2250.
-
iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervision
iSAGE achieves near-dense mIoU performance in remote sensing semantic segmentation using iterative expert clicks on confident model errors with an error-weighted loss, using only 0.011-0.04% of pixels.
-
Continuous Language Diffusion as a Decoder-Interface Problem
Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.
-
When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models
S³E framework finds excess decision-state displacement under semantic stress in multimodal models despite consistent correct forced-choice behavior.
-
Text-to-Image Models Need Less from Text Encoders Than You Think
A bag-of-position-tagged-words embedding guides text-to-image diffusion models as effectively as full contextual text embeddings from standard encoders.
-
SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory
SuperMemory-VQA provides 4,853 human-verified QA pairs from 52.9 hours of egocentric AI glasses recordings to benchmark AI systems on realistic long-horizon memory tasks including an unanswerable option.
-
Subgrid Marching Tetrahedra
Subgrid marching tetrahedra generalizes normal coordinates to encode arbitrary surface intersections per grid edge, enabling manifold mesh recovery without Nyquist limits.
-
GLENS: Global Search via Learning from Solver Iterates with Diffusion Models
GLENS uses diffusion models on solver iterates to generate high-quality and diverse initial guesses for multimodal non-convex optimization, leading to faster solver convergence.
-
HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control
HumanFlow is a latent diffusion model for unified human motion tracking and forecasting in 3D scenes, tightly coupled via flow-matching MPC to an approximate policy for MAV social navigation that outperforms prior methods in simulation under partial observability.
-
Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions
Introduces a unified benchmark for continual anomaly detection with discrete and continuous protocols plus a training-free DINOSaur method that outperforms prior CAD approaches with zero forgetting and sub-100ms edge inference.
-
RS2AD-LiDAR: End-to-End Autonomous Driving LiDAR Data Generation from Roadside Sensor Observations
RS2AD-LiDAR reconstructs vehicle LiDAR data from roadside observations via coordinate transformation, virtual LiDAR modeling and resampling, claimed as the first such method, with experiments showing improved object detection when mixed with real data.
-
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance
iTryOn is a diffusion-based framework that adds spatial 3D hand guidance and semantic action-aware embeddings to handle complex garment deformations during human-clothing interactions in videos.
-
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
-
Towards Principled Test-Time Adaptation for Time Series Forecasting
Proposes a matured-ground-truth TTA protocol and Frequency-Aware Calibration (FAC) that achieves competitive performance with substantially fewer parameters than prior TSF-TTA adapters.
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
SOLAR learns symmetric MM2MM embeddings self-supervised by disentangling image-text intersection masks then using them to auto-generate contrastive samples, outperforming 10 SOTA models including large VLMs on a new 214-triplet benchmark.
-
PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting
PanoPlane achieves up to 17.8% PSNR gains in sparse-view indoor novel view synthesis by using training-free plane-aware panoramic completion to supervise 3D Gaussian Splatting.
-
Covariance-aware sampling for Diffusion Models
A covariance-aware extension of DDIM sampling for pixel-space diffusion models that uses Tweedie's formula and Fourier decomposition to model reverse-process covariance and improves sample quality at low NFE.
-
Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning
A W-Net deep learning model detects asteroids in TESS data independently of trajectory by rotating training image cubes and using adaptive normalization for data scaling.
-
When Brains Disagree: Biological Ambiguity Underlies the Challenge of Amyloid PET Synthesis from Structural MRI
Biological ambiguity from temporally decoupled neurodegeneration and amyloid pathology creates one-to-many mappings that make MRI-to-amyloid PET synthesis intrinsically ill-posed, with performance restored by multimodal inputs.
-
Martingale-Consistent Self-Supervised Learning
The paper develops a martingale-consistent SSL framework enforcing expected coherence between coarse and refined predictions via new objectives and a Monte Carlo estimator, improving robustness under partial observations.
-
AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation
AnomalyClaw turns single-step VLM anomaly judgments into a multi-round tool-grounded refutation process, delivering consistent macro-AUROC gains of 3.5-7.9 percentage points over direct inference across 12 cross-domain datasets.
-
Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
LMMs perceive videos but underexploit visual content for causal reasoning due to textual shortcuts; ProCauEval diagnoses this and ADPO training reduces reliance on priors.
-
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.
-
COPYCOP: Ownership Verification for Graph Neural Networks
COPYCOP identifies copycat GNNs by matching their node embeddings despite architectural differences and adversarial transformations, backed by theoretical guarantees and tests on 14 datasets across 5 architectures.