WildBox provides over 237k 3D wildlife annotations from drone video and benchmarks reveal zero-shot 3D detection at 0 AP but fine-tuned performance of 8.68 AP-BEV and 13.17 AP3D, with depth estimation causing most errors.
super hub Canonical reference
In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Canonical reference. 77% of citing Pith papers cite this work as background.
246
Pith papers citing it
360
external citations · external index
Background
77% of classified citations
hub tools
citation-role summary
background 44
method 10
baseline 2
dataset 1
citation-polarity summary
authors
co-cited works
representative citing papers
SEVerA uses Formally Guarded Generative Models and a three-stage Search-Verification-Learning process to synthesize self-evolving agents that satisfy hard formal constraints while improving task performance.
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.
QVal is a new evaluation framework that directly measures dense supervision quality via Q-alignment to a reference policy, showing simple prompting baselines outperform 21 other methods across environments and models.
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.
An asynchronous architecture decouples incremental voxel-based mapping from VLM-based semantic enrichment to produce queryable open-vocabulary 3D scene graphs that match or exceed prior methods on segmentation and grounding benchmarks.
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.
SonoCLIP presents a mask-guided region-aware vision-language foundation model pretrained on 1.44M fetal ultrasound images, demonstrating superior zero-shot performance.
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.
AirGroundBench is a new diagnostic benchmark exposing that MLLMs handle basic spatial perception but struggle with cross-view alignment, transformation reasoning, and embodied navigation under heterogeneous air-ground views.
Provides a finite-sample minimax characterization of black-box assisted regression with a phase transition at δ_c(n) ~ n^{-β/(2β+d)} and a safe residual estimator achieving near-optimal risk.
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.
Line-Aligning Yaw Scoring recovers sub-degree yaw under ±20 m location noise and ±180° heading ambiguity by radially invariant column-to-line voting without height or known-position assumptions.
HERO maps DNA methylation and miRNA to a 16-dimensional intent vector for TF-IDF caption retrieval and cosine-gated repair in VLM-based multi-task breast cancer prediction, claiming SOTA on TCGA-BRCA.
WireCraft is a new configurable simulation benchmark for industrial DLO manipulation with three task families, dual physics models, and shared evaluation of RL, IL, and VLA policies showing high success under privileged state but bottlenecks for vision-based methods.
CloudLULC-Net is an end-to-end heterogeneous SAR-optical fusion network for LULC mapping under cloud contamination that achieves 86.60% OA, 83.29% F1, and 73.51% mIoU on a new global benchmark of 40,223 samples.
Introduces zero-inflated Gaussian distributions for EDAs to jointly optimize sparsity patterns and active parameter values without bi-level schemes or custom operators.
FisherAdapTune uses temporal drift in Fisher geometry, measured by scale-invariant Jensen-Shannon distance, to progressively freeze stabilized parameter groups during fine-tuning, reporting gains on segmentation and zero-shot transfer.
An ILP-based oracle applied to seven VIS methods on YouTube-VIS and OVIS shows tracking instability as the dominant bottleneck, producing gaps exceeding 20 AP under occlusion while classification impact is secondary.
Sensitivity-conditioned Bernoulli flow matching achieves state-of-the-art OOD generalization in topology optimization by preserving information about adjoint sensitivities, as predicted by the Data Processing Inequality.
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.
citing papers explorer
-
WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
WildBox provides over 237k 3D wildlife annotations from drone video and benchmarks reveal zero-shot 3D detection at 0 AP but fine-tuned performance of 8.68 AP-BEV and 13.17 AP3D, with depth estimation causing most errors.
-
SEVerA: Verified Synthesis of Self-Evolving Agents
SEVerA uses Formally Guarded Generative Models and a three-stage Search-Verification-Learning process to synthesize self-evolving agents that satisfy hard formal constraints while improving task performance.
-
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.
-
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
QVal is a new evaluation framework that directly measures dense supervision quality via Q-alignment to a reference policy, showing simple prompting baselines outperform 21 other methods across environments and models.
-
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.
-
Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs
An asynchronous architecture decouples incremental voxel-based mapping from VLM-based semantic enrichment to produce queryable open-vocabulary 3D scene graphs that match or exceed prior methods on segmentation and grounding benchmarks.
-
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.
-
SonoCLIP: Mask-Guided Region-Aware Vision-Language Pretraining for Fetal Ultrasound Analysis
SonoCLIP presents a mask-guided region-aware vision-language foundation model pretrained on 1.44M fetal ultrasound images, demonstrating superior zero-shot performance.
-
From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs
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.
-
AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration
AirGroundBench is a new diagnostic benchmark exposing that MLLMs handle basic spatial perception but struggle with cross-view alignment, transformation reasoning, and embodied navigation under heterogeneous air-ground views.
-
Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
Provides a finite-sample minimax characterization of black-box assisted regression with a phase transition at δ_c(n) ~ n^{-β/(2β+d)} and a safe residual estimator achieving near-optimal risk.
-
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.
-
Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring
Line-Aligning Yaw Scoring recovers sub-degree yaw under ±20 m location noise and ±180° heading ambiguity by radially invariant column-to-line voting without height or known-position assumptions.
-
HERO: Hypothesis-Driven Evidence Retrieval from Omics for Multi-Task Breast Cancer Analysis
HERO maps DNA methylation and miRNA to a 16-dimensional intent vector for TF-IDF caption retrieval and cosine-gated repair in VLM-based multi-task breast cancer prediction, claiming SOTA on TCGA-BRCA.
-
WireCraft: A Simulation Benchmark for Industrial DLO Manipulation
WireCraft is a new configurable simulation benchmark for industrial DLO manipulation with three task families, dual physics models, and shared evaluation of RL, IL, and VLA policies showing high success under privileged state but bottlenecks for vision-based methods.
-
Heterogeneous SAR-optical fusion for near-real-time land use and land cover mapping under cloud contamination: A novel framework and global benchmark dataset
CloudLULC-Net is an end-to-end heterogeneous SAR-optical fusion network for LULC mapping under cloud contamination that achieves 86.60% OA, 83.29% F1, and 73.51% mIoU on a new global benchmark of 40,223 samples.
-
Zero-Inflated Gaussian Distributions Enable Parameter-Space Sparsity in Estimation-of-Distribution Algorithms
Introduces zero-inflated Gaussian distributions for EDAs to jointly optimize sparsity patterns and active parameter values without bi-level schemes or custom operators.
-
Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning
FisherAdapTune uses temporal drift in Fisher geometry, measured by scale-invariant Jensen-Shannon distance, to progressively freeze stabilized parameter groups during fine-tuning, reporting gains on segmentation and zero-shot transfer.
-
Mind the Gap: Disentangling Performance Bottlenecks in Video Instance Segmentation
An ILP-based oracle applied to seven VIS methods on YouTube-VIS and OVIS shows tracking instability as the dominant bottleneck, producing gaps exceeding 20 AP under occlusion while classification impact is secondary.
-
On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow Matching
Sensitivity-conditioned Bernoulli flow matching achieves state-of-the-art OOD generalization in topology optimization by preserving information about adjoint sensitivities, as predicted by the Data Processing Inequality.
-
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.
-
Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
Text knowledge edits in UMMs reach 92% text efficacy but only 18.5% VQA accuracy on images, with reasoning-augmented editing narrowing the cross-modal gap.
-
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.
-
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.
-
CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration
CoMoGen generates controllable interactive video from mask sequences and images by encoding masks into MMDiT via MaskAdapter and LoRA on motion layers, claiming SOTA motion fidelity.
-
LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue
LMM-Track4D formulates a trajectory-grounded dialogue task, releases Track4D-Bench with 526 samples, and proposes RTGE encoding, TRK state token, and OSK-RA decoder to elicit better 4D spatiotemporal reasoning in LMMs.
-
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.
-
Navigating Potholes with Geometry-Aware Sharpness Minimization
LLQR+SAM pairs a slow learned geometry preconditioner with fast SAM perturbations to amplify escape from locally sharp 'potholes' while stabilizing flat basins, producing consistent gains over SAM and LLQR alone.
-
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.
-
OffsetAxis: UDF Mesh Reconstruction via Offset-Volume Medial Axis Extraction
OffsetAxis reconstructs meshes from unsigned distance fields by extracting the medial axis of the alpha-offset volume using ray casting and variational medial ball optimization.
-
NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework
A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures.
-
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
DiHAL uses geometry proxies to pick where to replace the lower layers of a pretrained transformer with a diffusion bridge for hidden-state reconstruction, improving over token-level diffusion baselines on 8B models.
-
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.
-
Same Image, Different Meanings: Toward Retrieval of Context-Dependent Meanings
Image meanings grow more context-dependent with semantic abstraction, requiring narrative grounding for accurate retrieval at higher levels.
-
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.
-
Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
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.
-
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.
-
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
Driver-WM is a driver-centric latent world model for causal rollout of in-cabin dynamics conditioned on out-cabin traffic, unifying kinematics forecasting with behavioral and emotional recognition via dual-stream architecture and gated injection.
-
Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
-
CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint
CSGuard binds diffusion-model watermarks to a secret matrix via compressed sensing, cutting forgery attack success from 100% to 28.12% while preserving 100% detection on legitimate images.
-
SyMTRS: Benchmark Multi-Task Synthetic Dataset for Depth, Domain Adaptation and Super-Resolution in Aerial Imagery
A new large-scale synthetic multi-task benchmark dataset supplying pixel-perfect depth, domain-shifted night imagery, and multi-scale low-resolution pairs for aerial remote sensing.
-
AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
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.
-
HumanScore: Benchmarking Human Motions in Generated Videos
HumanScore defines six metrics for kinematic plausibility, temporal stability, and biomechanical consistency to benchmark human motions in videos from thirteen state-of-the-art generation models, revealing gaps between visual appeal and physical fidelity.
-
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
-
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
AnchorSeg uses ordered query banks of latent reasoning tokens plus a spatial anchor token and a Token-Mask Cycle Consistency loss to achieve 67.7% gIoU and 68.1% cIoU on the ReasonSeg benchmark.
-
Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes
SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.