Q-Margin encodes margin penalties into the reference measure of an alpha-divergence loss to produce sparse discriminative embeddings for face and speaker verification.
hub Mixed citations
In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pp
Mixed citation behavior. Most common role is background (38%).
25
Pith papers citing it
Background
38% of classified citations
hub tools
citation-role summary
background 3
dataset 3
method 2
citation-polarity summary
representative citing papers
ESARBench is the first unified benchmark for MLLM-driven UAV agents that must explore, locate clues, and decide on victim positions in photorealistic simulated SAR environments.
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
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.
A two-stage diffusion framework generates a layout-controllable low-resolution blueprint to guide parallel high-resolution artwork outpainting, achieving 2.4× speedup and improved fidelity over sequential baselines.
NURBS Splatting represents rational splines as continuous Gaussian fields sampled along the curve to enable stable differentiable rendering of vector graphics.
Scene-adaptive nonlinear tone curves (ASE and AP3) with percentile normalisation and offset outperform linear gain for pseudo-GT generation in low-light 3DGS, delivering PSNR gains up to 4.34 dB on LOM and 3.25 dB on RealX3D across 21 scenes.
Primary-path enclosure plus τ_exp-aligned fusion on a Dual-SoC AD-ECU yields 296 ms mean shutter-to-planner latency within a 350 ms budget while co-running modular and E2E paths.
Introduces CausalPhys benchmark with causal graphs and CRFT fine-tuning to improve VLMs' causal physical reasoning accuracy and interpretability.
SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.
Robots discover causal tool features through VLM suggestions and physics-based counterfactual perturbations in simulation, then transfer manipulation skills via conditioned keypoint matching.
CustomDancer achieves state-of-the-art text-to-dance retrieval with 10.23% Recall@1 on the new TD-Data dataset by aligning text, music, and motion features through a CLIP-based framework.
The ICPR 2026 LRLPR competition on real low-quality license plate images drew 99 valid submissions, with the winning team reaching 82.13% recognition rate and four teams exceeding 80%.
GOLD-BEV learns dense BEV semantic maps including dynamic agents from ego-centric sensors by using synchronized aerial imagery for training supervision and pseudo-label generation.
A parser-oriented refinement stage performs set-level reasoning on detector hypotheses to jointly decide instance retention, refine boxes, and set parser input order, cutting reading order errors to 0.024 on OmniDocBench.
ERIS partitions client updates into shards aggregated across multiple client-side nodes to reduce communication bottlenecks, limit information exposure, and preserve FedAvg-level utility while improving resistance to inference attacks.
ViTaPEs uses two-stage positional encodings in a multimodal transformer to learn task-agnostic visuotactile representations that outperform baselines on recognition tasks, show zero-shot generalization, and improve robotic grasp success prediction.
FedLAS adds feature-norm based confidence detection and bidirectional gating to label smoothing losses to reduce calibration error on vision benchmarks while preserving accuracy.
HP-VSR-ResFiLM adds a single residual FiLM modulation block conditioned on head pose to a CNN visual encoder, yielding WER of 25.0% on LRS2 and 33.2% on LRS3 under standard training conditions.
TRACER applies weighted moving average distillation in contrastive finetuning of multimodal models to retain pretrained knowledge and boost out-of-distribution accuracy.
Frozen DINOv2-L features with k-NN classification and PCA/ICA refinement achieve state-of-the-art few-shot performance on four benchmarks without any backpropagation or fine-tuning.
GameAD models autonomous driving as a risk-prioritized game among agents via Risk-Aware Topology Anchoring, Minimax Risk-Aware Sparse Attention and related components, yielding safer trajectories than prior end-to-end methods on nuScenes and Bench2Drive.
Empirical benchmark finds attention-based models (SwinTiny, CoAtNet0, MaxViTTiny) achieve highest AUC above 84% on RFMiD binary screening and best F1 scores on multi-label task, with VLMs competitive but not superior and external Messidor-2 AUC 66.8-84.7%.
citing papers explorer
-
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.
-
ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue
ESARBench is the first unified benchmark for MLLM-driven UAV agents that must explore, locate clues, and decide on victim positions in photorealistic simulated SAR environments.
-
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
-
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.
-
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.
-
High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control
A two-stage diffusion framework generates a layout-controllable low-resolution blueprint to guide parallel high-resolution artwork outpainting, achieving 2.4× speedup and improved fidelity over sequential baselines.
-
NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics
NURBS Splatting represents rational splines as continuous Gaussian fields sampled along the curve to enable stable differentiable rendering of vector graphics.
-
Scene-Adaptive Nonlinear Tone Curves for Pseudo Ground-Truth Generation in Low-Light 3D Gaussian Splatting
Scene-adaptive nonlinear tone curves (ASE and AP3) with percentile normalisation and offset outperform linear gain for pseudo-GT generation in low-light 3DGS, delivering PSNR gains up to 4.34 dB on LOM and 3.25 dB on RealX3D across 21 scenes.
-
An Exposure-Time-Aligned Primary-Path Architecture for Autonomous-Driving ECUs
Primary-path enclosure plus τ_exp-aligned fusion on a Dual-SoC AD-ECU yields 296 ms mean shutter-to-planner latency within a 350 ms budget while co-running modular and E2E paths.
-
Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs
Introduces CausalPhys benchmark with causal graphs and CRFT fine-tuning to improve VLMs' causal physical reasoning accuracy and interpretability.
-
SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation
SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.
-
Creative Robot Tool Use by Counterfactual Reasoning
Robots discover causal tool features through VLM suggestions and physics-based counterfactual perturbations in simulation, then transfer manipulation skills via conditioned keypoint matching.
-
CustomDancer: Customized Dance Recommendation by Text-Dance Retrieval
CustomDancer achieves state-of-the-art text-to-dance retrieval with 10.23% Recall@1 on the new TD-Data dataset by aligning text, music, and motion features through a CLIP-based framework.
-
ICPR 2026 Competition on Low-Resolution License Plate Recognition
The ICPR 2026 LRLPR competition on real low-quality license plate images drew 99 valid submissions, with the winning team reaching 82.13% recognition rate and four teams exceeding 80%.
-
GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes
GOLD-BEV learns dense BEV semantic maps including dynamic agents from ego-centric sensors by using synchronized aerial imagery for training supervision and pseudo-label generation.
-
Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
A parser-oriented refinement stage performs set-level reasoning on detector hypotheses to jointly decide instance retention, refine boxes, and set parser input order, cutting reading order errors to 0.024 on OmniDocBench.
-
ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
ERIS partitions client updates into shards aggregated across multiple client-side nodes to reduce communication bottlenecks, limit information exposure, and preserve FedAvg-level utility while improving resistance to inference attacks.
-
ViTaPEs: Visuotactile Position Encodings for Cross-Modal Alignment in Multimodal Transformers
ViTaPEs uses two-stage positional encodings in a multimodal transformer to learn task-agnostic visuotactile representations that outperform baselines on recognition tasks, show zero-shot generalization, and improve robotic grasp success prediction.
-
FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration
FedLAS adds feature-norm based confidence detection and bidirectional gating to label smoothing losses to reduce calibration error on vision benchmarks while preserving accuracy.
-
Head-Pose-Aware Visual Speech Recognition with FiLM Modulation
HP-VSR-ResFiLM adds a single residual FiLM modulation block conditioned on head pose to a CNN visual encoder, yielding WER of 25.0% on LRS2 and 33.2% on LRS3 under standard training conditions.
-
TRACER: Persistent Regularization for Robust Multimodal Finetuning
TRACER applies weighted moving average distillation in contrastive finetuning of multimodal models to retain pretrained knowledge and boost out-of-distribution accuracy.
-
Rethinking the Good Enough Embedding for Easy Few-Shot Learning
Frozen DINOv2-L features with k-NN classification and PCA/ICA refinement achieve state-of-the-art few-shot performance on four benchmarks without any backpropagation or fine-tuning.
-
Not All Agents Matter: From Global Attention Dilution to Risk-Prioritized Game Planning
GameAD models autonomous driving as a risk-prioritized game among agents via Risk-Aware Topology Anchoring, Minimax Risk-Aware Sparse Attention and related components, yielding safer trajectories than prior end-to-end methods on nuScenes and Bench2Drive.
-
Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening
Empirical benchmark finds attention-based models (SwinTiny, CoAtNet0, MaxViTTiny) achieve highest AUC above 84% on RFMiD binary screening and best F1 scores on multi-label task, with VLMs competitive but not superior and external Messidor-2 AUC 66.8-84.7%.
-
Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding
A literature survey on abstract concept recognition in videos that catalogs prior tasks and datasets while advocating for foundation models and reuse of decades of community experience.