Injecting pre-computed layout priors from RT-DETR into VLM prompts raises markdown F1 from 0.37 to 0.92 on a 10k-page OOD benchmark and cuts infinite-loop failures across domains.
hub
You only look once: Unified, real-time object detection
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
abstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.
CROWD is a new global dataset of 51,753 continuous urban dashcam segments spanning over 20,000 hours from 238 countries, with manual labels and automated object detections for routine driving analysis.
SAME-Net adds a differentiable soft attention mask embedding module to achieve rectification-free end-to-end scene text spotting with 84.02% H-mean on Total-Text.
AFFORD2ACT distills a minimal set of affordance-guided 2D keypoints from text and a single image to train a 38-dimensional gated transformer policy that achieves 82% success on unseen objects and scenes.
Presents an end-to-end multitask CNN with FPN, dynamic RoI pooling, and convolutional attention for simultaneous lexicon-free text localization and recognition in complex images.
DroneScan-YOLO reaches 55.3% mAP@50 and 35.6% mAP@50-95 on VisDrone2019-DET by combining 1280x1280 input, RPA-Block pruning, MSFD stride-4 branch, and SAL-NWD loss, beating YOLOv8s by 16.6 and 12.3 points with only 4.1% more parameters.
CODO automates comprehensive dataflow optimization on FPGAs, achieving 1.45x-4.52x speedups on kernels and up to 33.8x on DNN models over state-of-the-art frameworks.
VLM-based harmonization of inconsistent annotations across two document layout corpora raises detection F-score from 0.860 to 0.883 and table TEDS from 0.750 to 0.814 while tightening embedding clusters.
Entropy-gradient grounding uses model uncertainty to retrieve evidence regions in VLMs, improving performance on detail-critical and compositional tasks across multiple architectures.
The OSS Challenge provides benchmarks showing spatiotemporal video models excel at open suturing skill classification and OSATS scoring but struggle with keypoint tracking under occlusion.
Deep learning analysis of fast imaging data indicates most negative fluctuation structures in COMPASS tokamak plasma are artifacts from sliding-median subtraction, while supernumerary negatives exhibit expected hole dynamics.
A CNN detects 19,685 LAEs at z=2-3.5 in DESI DR1 spectra with 95% purity and completeness.
RobustTP uses a non-linear motion model plus instance segmentation to create noisy trajectories, then an LSTM-CNN to predict 5-second future positions of heterogeneous agents in dense traffic, claiming up to 18% ADE and 35.5% FDE gains over prior methods.
GarmNet jointly localizes garments and detects grasp landmarks on the CloPeMa dataset, reducing localization error by 24.7% when landmark detection is included.
A pipeline uses OpenPose and Gaze-LLE to extract pose and gaze data from classroom videos, deletes the raw footage, and applies an LLM for zero-shot behavioral analysis of student attention.
Logistic regression on frozen DINOv3 features achieves 88.5% macro F1 on the AQUA20 marine species benchmark, matching end-to-end supervised models with only 6% of the labels.
Cello Evaluator is a real-time postural feedback system for cellists running on current Android phones via on-device computer vision, validated as user-friendly by experts.
A system combining object detection, segmentation, keypoint prediction, and homography transforms soccer video into real-world player positions and tactical statistics.
citing papers explorer
-
Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding
Injecting pre-computed layout priors from RT-DETR into VLM prompts raises markdown F1 from 0.37 to 0.92 on a 10k-page OOD benchmark and cuts infinite-loop failures across domains.
-
Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis
QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.
-
A global dataset of continuous urban dashcam driving
CROWD is a new global dataset of 51,753 continuous urban dashcam segments spanning over 20,000 hours from 238 countries, with manual labels and automated object detections for routine driving analysis.
-
Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
SAME-Net adds a differentiable soft attention mask embedding module to achieve rectification-free end-to-end scene text spotting with 84.02% H-mean on Total-Text.
-
AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation
AFFORD2ACT distills a minimal set of affordance-guided 2D keypoints from text and a single image to train a 38-dimensional gated transformer policy that achieves 82% success on unseen objects and scenes.
-
A Multitask Network for Localization and Recognition of Text in Images
Presents an end-to-end multitask CNN with FPN, dynamic RoI pooling, and convolutional attention for simultaneous lexicon-free text localization and recognition in complex images.
-
DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery
DroneScan-YOLO reaches 55.3% mAP@50 and 35.6% mAP@50-95 on VisDrone2019-DET by combining 1280x1280 input, RPA-Block pruning, MSFD stride-4 branch, and SAL-NWD loss, beating YOLOv8s by 16.6 and 12.3 points with only 4.1% more parameters.
-
CODO: An Automated Compiler for Comprehensive Dataflow Optimization
CODO automates comprehensive dataflow optimization on FPGAs, achieving 1.45x-4.52x speedups on kernels and up to 33.8x on DNN models over state-of-the-art frameworks.
-
Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization
VLM-based harmonization of inconsistent annotations across two document layout corpora raises detection F-score from 0.860 to 0.883 and table TEDS from 0.750 to 0.814 while tightening embedding clusters.
-
Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
Entropy-gradient grounding uses model uncertainty to retrieve evidence regions in VLMs, improving performance on detail-critical and compositional tasks across multiple architectures.
-
OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025
The OSS Challenge provides benchmarks showing spatiotemporal video models excel at open suturing skill classification and OSATS scoring but struggle with keypoint tracking under occlusion.
-
Comparative blobs and holes dynamics in a tokamak plasma: deep learning analysis of fast imaging data
Deep learning analysis of fast imaging data indicates most negative fluctuation structures in COMPASS tokamak plasma are artifacts from sliding-median subtraction, while supernumerary negatives exhibit expected hole dynamics.
-
Unveiling Hidden Lyman Alpha Emitters in the DESI DR1 Data
A CNN detects 19,685 LAEs at z=2-3.5 in DESI DR1 spectra with 95% purity and completeness.
-
RobustTP: End-to-End Trajectory Prediction for Heterogeneous Road-Agents in Dense Traffic with Noisy Sensor Inputs
RobustTP uses a non-linear motion model plus instance segmentation to create noisy trajectories, then an LSTM-CNN to predict 5-second future positions of heterogeneous agents in dense traffic, claiming up to 18% ADE and 35.5% FDE gains over prior methods.
-
GarmNet: Improving Global with Local Perception for Robotic Laundry Folding
GarmNet jointly localizes garments and detects grasp landmarks on the CloPeMa dataset, reducing localization error by 24.7% when landmark detection is included.
-
Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
A pipeline uses OpenPose and Gaze-LLE to extract pose and gaze data from classroom videos, deletes the raw footage, and applies an LLM for zero-shot behavioral analysis of student attention.
-
Label-efficient underwater species classification with logistic regression on frozen foundation model embeddings
Logistic regression on frozen DINOv3 features achieves 88.5% macro F1 on the AQUA20 marine species benchmark, matching end-to-end supervised models with only 6% of the labels.
-
Real-Time Cellist Postural Evaluation With On-Device Computer Vision
Cello Evaluator is a real-time postural feedback system for cellists running on current Android phones via on-device computer vision, validated as user-friendly by experts.
-
AI Driven Soccer Analysis Using Computer Vision
A system combining object detection, segmentation, keypoint prediction, and homography transforms soccer video into real-world player positions and tactical statistics.