arXiv Computer Vision
Input Resolution Matters: Real-Time Object Detection Latency
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 21
YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions
arXiv:2608. 04720v4 Announce Type: replace Abstract: Real-time object detectors achieve remarkable accuracy under controlled conditions, yet degrade sharply on non-ideal inputs-fisheye distortion, game-rendered content, aerial views, and 360{\deg}panoramas.
arXiv Machine Learning
Sep 25
Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge
Albireo is an adaptive, energy‑efficient inference framework for video object detection on edge devices that wraps existing detectors without modification. It uses a 10‑dimensional Kalman filter per active object to decide when to skip detector calls, predicting bounding boxes on skipped frames at near‑zero GPU cost. Evaluated on BDD100K with YOLO and RF‑DETR detectors on NVIDIA Jetson AGX Thor and Orin, Albireo maintains AP@50 within ±1.2 pp of full‑frame inference while reducing energy consumption by 12.1–17.6 % and improving accuracy for some models.
arXiv AI
Jun 3
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
arXiv:2606. 03748v1 Announce Type: cross Abstract: Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware.
arXiv AI
Jul 1
Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors
arXiv:2606. 31421v1 Announce Type: cross Abstract: Single-stage video object detectors are increasingly deployed in time-critical applications, yet it remains unclear whether these models genuinely reason over temporal context or merely exploit a single informative frame-a gap hidden by standard metrics, which reward correct predictions regardless of how they are reached.
arXiv AI
Jun 29
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
arXiv:2606. 27978v1 Announce Type: cross Abstract: Pixel-space continuous-token autoregressive (AR) generation directly models images as sequences of raw pixel patches, avoiding discrete tokenization or a separately pretrained tokenizer.
arXiv AI
Jun 2
CARES: Context-Aware Resolution Selector for VLMs
arXiv:2510. 19496v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks.