Computer Vision

arXiv:2505.23617v3 Announce Type: replace-cross Abstract: Effective video tokenization is critical for scaling transformer models for long videos. Current appro

arXiv:2603.14694v2 Announce Type: replace-cross Abstract: Rapid structural damage assessment from remote sensing imagery is essential for timely disaster respon

One camera feed. Real Tesla footage. A full 3D world. Continue reading on Medium »

A step‑by‑step guide to train, containerize, and serve a custom YOLOv8 model with low‑latency FastAPI endpoints, Docker, and GitHub Actions

Validating Passport Photos for 3 of the Strictest Government Portals (India, China,...

arXiv:2605.06714v1 Announce Type: cross Abstract: Edge deep learning, a paradigm change reconciling edge computing and deep learning, facilitates real-time deci

arXiv:2605.06927v1 Announce Type: cross Abstract: Object detection on heterogeneous edge devices must satisfy strict energy, latency, and memory constraints whi

arXiv:2605.07151v1 Announce Type: cross Abstract: Urban spatial evolution is manifested not only through horizontal expansion but also through vertical structur

arXiv:2605.07317v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-preci

arXiv:2605.07604v1 Announce Type: cross Abstract: 3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions,

arXiv:2605.07786v1 Announce Type: cross Abstract: As generative models achieve unprecedented visual quality, the gold standard for image evaluation remains trad

arXiv:2605.07897v1 Announce Type: cross Abstract: Online streaming video understanding requires models to process continuous visual inputs and respond to user q

arXiv:2605.08043v1 Announce Type: cross Abstract: While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual i

arXiv:2605.08073v1 Announce Type: cross Abstract: Recent event-based image reconstruction methods predominantly rely on Convolutional Neural Networks (CNNs) and

arXiv:2509.12047v2 Announce Type: replace-cross Abstract: Animal behavior analysis plays a crucial role in understanding animal welfare, health status, and prod

arXiv:2601.15356v5 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has empowered Multimodal Large Language Models (MLLMs) to achieve superior

arXiv:2603.12647v2 Announce Type: replace-cross Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene re

arXiv:2603.21824v2 Announce Type: replace-cross Abstract: Steel surface defect analysis is critical for industrial quality control, yet existing benchmarks rely

Research papers on pose estimation show impressive accuracy numbers. Production apps on consumer...

This project speaks for itself. It covers three crucial steps in one go: motion tracking, skeleton reconstruction, and 3D animation. What… Continue reading on M

The Problem Converting a photo into a LEGO mosaic sounds simple: resize the image, find...

Seminar #5 (Paper review) Continue reading on Medium »

## Why I wrote this experiment Continue reading on Medium »

Understanding how Convolutional Neural Networks transform raw pixel data into intelligent predictions. Continue reading on Medium »

What if navigation systems could remember routes visually instead of depending entirely on...

The models, the stack, the ROI — no fluff Continue reading on Medium »

Conquering the nightmare of Borderless, Scanned, and Merged-Cell Tables with a Hybrid AI Pipeline Continue reading on Medium »

arXiv:2605.05402v1 Announce Type: new Abstract: Artificial intelligence (AI) and computer vision are transforming transportation data collection. This study int

arXiv:2605.05832v1 Announce Type: new Abstract: Optical Chemical Structure Recognition (OCSR) aims to translate molecular diagrams in scientific literature into

arXiv:2605.05367v1 Announce Type: cross Abstract: Arabic Sign Language (ArSL) and its dialects serve approximately 400 million Arabic speakers worldwide, yet th

arXiv:2605.05692v1 Announce Type: cross Abstract: Privacy-preserving action recognition (PPAR) enables machines to understand human activities in videos without

arXiv:2605.05775v1 Announce Type: cross Abstract: We report the design and results of the third autoPET challenge (MICCAI 2024), which benchmarked automated les

arXiv:2605.05848v1 Announce Type: cross Abstract: Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long

arXiv:2605.05990v1 Announce Type: cross Abstract: Motion blur restoration on consumer mobile devices is typically evaluated using aggregate metrics that obscure

arXiv:2605.06010v1 Announce Type: cross Abstract: Purely RGB-based vision models often fail to provide reliable cues in challenging scenarios such as nighttime

arXiv:2605.06112v1 Announce Type: cross Abstract: Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as

arXiv:2605.06137v1 Announce Type: cross Abstract: In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive

arXiv:2605.06667v1 Announce Type: cross Abstract: For artistic applications, video generation requires fine-grained control over both performance and cinematogr

arXiv:2506.18682v2 Announce Type: replace-cross Abstract: Recent advances in autonomous driving (AD) have highlighted the potential of hyperspectral imaging (HS

arXiv:2512.11016v2 Announce Type: replace-cross Abstract: Soccer understanding has recently garnered growing research interest due to its domain-specific comple

arXiv:2601.03728v2 Announce Type: replace-cross Abstract: Composed Image Retrieval (CIR) enables users to search for target images using both a reference image

arXiv:2603.06351v2 Announce Type: replace-cross Abstract: Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth

arXiv:2603.14209v2 Announce Type: replace-cross Abstract: A pictorial chart is an effective medium for visual storytelling, seamlessly integrating visual elemen

There are four widely used number systems: decimal (10), binary (2), octal (8), and hexadecimal (16). As humans, we use the decimal system. Continue reading on

Mengapa Pencahayaan Itu Krusial? ​Pernahkah Anda mengambil foto di kondisi minim cahaya dan mendapati hasilnya sangat gelap hingga… Continue reading on Medium »

In the rapidly evolving landscape of artificial intelligence, selecting the optimal architecture for computer vision is rarely a simple… Continue reading on Obj

The landmark designs that shaped modern computer vision, from LeNet to EfficientNet. Continue reading on Medium »

There’s a scene in Life of Pi where the ocean at night fills with bioluminescent green light. The whole frame glows. It’s one of the most… Continue reading on M