Search Results for "video benchmark"
Sort By:
Showing 24 open source projects for "video benchmark"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
1
HunyuanWorld-Voyager
RGBD video generation model conditioned on camera input
HunyuanWorld-Voyager is a next-generation video diffusion framework developed by Tencent-Hunyuan for generating world-consistent 3D scene videos from a single input image. By leveraging user-defined camera paths, it enables immersive scene exploration and supports controllable video synthesis with high realism. The system jointly produces aligned RGB and depth video sequences, making it directly applicable to 3D reconstruction tasks. At its core, Voyager integrates a world-consistent video... -
2
Qwen2.5-Omni
Capable of understanding text, audio, vision, video
...Very strong benchmark performance across modalities (audio understanding, speech recognition, image/video reasoning) and often outperforming or matching single-modality models at a similar scale. Real-time streaming responses, including natural speech synthesis (text-to-speech) and chunked inputs for low latency interaction. -
3
SAM 3
Code for running inference and finetuning with SAM 3 model
SAM 3 (Segment Anything Model 3) is a unified foundation model for promptable segmentation in both images and videos, capable of detecting, segmenting, and tracking objects. It accepts both text prompts (open-vocabulary concepts like “red car” or “goalkeeper in white”) and visual prompts (points, boxes, masks) and returns high-quality masks, boxes, and scores for the requested concepts. Compared with SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an... -
4
LZ4
Extremely fast compression algorithm
...A high compression derivative, called LZ4_HC, is available, trading customizable CPU time for compression ratio. LZ4 library is provided as open-source software using a BSD license. This benchmark simulates simple "static content transfer" scenario such as OS Kernel compression or video game's static assets (text/images/tables/scripts/etc) which loading from Flash Memory / HDD / SSD. In this case, compression time is completely ignored. Because only content developers compress the data at once and usually they don't care about its computational cost. ... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
5
LLM Colosseum
Benchmark LLMs by fighting in Street Fighter 3
LLM-Colosseum is an experimental benchmarking framework designed to evaluate the capabilities of large language models through gameplay interactions rather than traditional text-based benchmarks. The system places language models inside the environment of the classic video game Street Fighter III, where they must interpret the game state and decide which actions to perform during combat. This setup creates a dynamic environment that tests reasoning, situational awareness, and decision-making... -
6
GLM-V
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning
GLM-V is an open-source vision-language model (VLM) series from ZhipuAI that extends the GLM foundation models into multimodal reasoning and perception. The repository provides both GLM-4.5V and GLM-4.1V models, designed to advance beyond basic perception toward higher-level reasoning, long-context understanding, and agent-based applications. GLM-4.5V builds on the flagship GLM-4.5-Air foundation (106B parameters, 12B active), achieving state-of-the-art results on 42 benchmarks across image,... -
7
HunyuanOCR
OCR expert VLM powered by Hunyuan's native multimodal architecture
...Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a wide variety of OCR tasks, outperforming many traditional OCR systems and even other multimodal models on benchmark suites. HunyuanOCR handles complex documents: multi-column layouts, tables, mathematical formulas, mixed languages, handwritten or stylized fonts, receipts, tickets, and even video-frame subtitles. The project provides code, pretrained weights, and inference instructions, making it feasible to deploy locally or on a server, and to integrate with applications. -
8
InternVL
A Pioneering Open-Source Alternative to GPT-4o
InternVL is a large-scale multimodal foundation model designed to integrate computer vision and language understanding within a unified architecture. The project focuses on scaling vision models and aligning them with large language models so that they can perform tasks involving both visual and textual information. InternVL is trained on massive collections of image-text data, enabling it to learn representations that capture both visual patterns and semantic meaning. The model supports a... -
9
DCV Color Primitives
DCV Color Primitives Library
DCV Color Primitives is a library to perform image color model conversion. Aware of the underlying hardware and supplemental cpu extension sets (up to avx2). Support data coming from a single buffer or coming from multiple image planes. Support non-tightly packed data. Support images greater than 4GB (64 bit). Convert an image from bgra to nv12 (single plane) format containing yuv in BT601. You might want to propagate errors to the caller function or mix with some other error types. So far,... -
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
10
FurMark
GPU stress test OpenGL and Vulkan graphics benchmark Windows/Linux
FurMark is an intensive benchmarking tool designed to evaluate the performance of graphics cards using fur rendering algorithms. This tool is particularly effective in generating high workloads that can significantly increase the temperature of the GPU, making it a useful utility for testing the stability and stress tolerance of graphics cards. By simulating demanding rendering tasks, FurMark serves as a comprehensive test for assessing the robustness and thermal performance of GPUs under... -
11
AI File Sorter
Local AI file organization with categorization and rename suggestions
AI File Sorter is a cross-platform desktop application that uses AI (local LLMs run on your computer) to organize files and suggest meaningful file names based on real content, not just filenames or extensions. The app can analyze images locally and propose descriptive rename suggestions (for example, IMG_2048.jpg → clouds_over_lake.jpg). It can also analyze document text to improve categorization and renaming. Supported formats include PDF, DOCX, XLSX, PPTX, ODT, ODS, ODP, and common... -
12
Animation Compression Library
Animation Compression Library
Animation compression is a fundamental aspect of modern video game engines. Not only is it important to keep the memory footprint down but it is also critical to keep the animation clip sampling performance fast. The more memory an animation clip consumes, the slower it will be to sample it and extract a character pose at runtime. For these reasons, any game that attempts to push the boundaries of what the hardware can achieve will at some point need to implement some form of animation... -
13
MMAction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
OpenMMLab's next generation video understanding toolbox and benchmark. MMAction2 is an open-source toolbox for video understanding based on PyTorch. It is a part of the OpenMMLab project. Modular design: We decompose a video understanding framework into different components. One can easily construct a customized video understanding framework by combining different modules. -
14
BasicSR
Winning Solution in NTIRE19 Challenges on Video Restoration
BasicSR is a deep learning framework designed for advanced video restoration tasks such as video super-resolution, deblurring, and denoising. Unlike single-image restoration models, EDVR addresses the temporal dimension by aligning multiple video frames using deformable convolutional layers in a coarse-to-fine manner, allowing it to effectively handle large motion and complex scene dynamics. The architecture includes bespoke modules (e.g., Pyramid, Cascading and Deformable alignment and... -
15
YouTube-8M
Starter code for working with the YouTube-8M dataset
youtube-8m is Google’s open source starter code and reference implementation for training and evaluating machine learning models on the YouTube-8M dataset, one of the largest video understanding datasets publicly released. The repository provides a complete pipeline for video-level and frame-level modeling using TensorFlow, including data reading, model training, evaluation, and inference. It was developed to support the YouTube-8M Video Understanding Challenge (hosted on Kaggle and featured at ICCV 2019), enabling researchers and practitioners to benchmark video classification models on large-scale datasets with over millions of labeled videos. ... -
16
I3D models trained on Kinetics
Convolutional neural network model for video classification
...This repository includes pretrained I3D models on the Kinetics dataset, with both RGB and optical flow input streams. The models have achieved state-of-the-art results on benchmark datasets such as UCF101 and HMDB51, and also won first place in the CVPR 2017 Charades Challenge. The project provides TensorFlow and Sonnet-based implementations, pretrained checkpoints, and example scripts for evaluating or fine-tuning models. It also offers sample data, including preprocessed video frames and optical flow arrays, to demonstrate how to run inference and visualize outputs. -
17
Video Nonlocal Net
Non-local Neural Networks for Video Classification
...Efficient implementations keep memory and compute manageable so the blocks can be added without rewriting the entire backbone. The result is a practical, drop-in mechanism for upgrading purely local video models into context-aware networks with strong benchmark performance. -
18
Simple Web Chat
Simple open source php based HTML5 rich web chat system
Its a high performance simple feature rich and fully customizable web based chat implemented using php and jquery with auto fall-back from HTML5 WebSocket to HTML5 SSE to Ajax Long Polling Can work with or without any database server and sessions It can be used as standalone or as module / plugin in any website Fetaures: 1) Registration, login, forgot password 2) Search and add contacts, manage groups 3) Broadcast, one to one & group chat 4) Desktop notification, sound alert, auto scroll to new message 5) Attachments, smileys 6) Multiple tab chat 7) Message History *Audio-Video chat using WebRTC integrated into code, but not yet tested All these managed without use of any database server. Its fully standalone but can be easily integrated with any database using a simple cron. Performance: Serves 1 lakh messages in approx 30 seconds (tested with apache benchmark utility) Visit http://pls-e.in/site/products#web-apps for more details or to contact us -
19
FRAFS Test Pattern
Simple Direct3D test pattern generator
Do you worry if Fraps (or other computer video capture tool) is giving you accurate colors? Do you wish you had some kind of standard, recordable (DirectX 9) source with known colors? Well, you're in luck, that's just what this is. **NOTE: monitor calibration software is known to alter capture colors** See the first screenshot for a guide to what's in this test pattern. It also includes some rare & unusual utilities; see below. -
20
FRAFS Bench Viewer
Simple viewer for Fraps 'frametimes' benchmark results
Fraps has the ability to tell us the amount of time each frame took to display. With this program, it becomes easy to view this information as a chart, in overview or in fine detail. Hopefully this will help the Fraps user community to spot troublesome hardware or software setups. -
21
A useful Multi-function Tool box. Clean Up System Drive, Print Task Quick Cancle,Schedule Auto Shutdown Computer,Schedule Auto Run Programs or Open files,IE (Internet Explorer) Repair and more funtion...(Only For Windows XP Vista Win7 X86 and X64)
-
22
Openmark will be a Open Source benchmark that will have 32/64 bit options for video rendering tests on X11 as well as HD speed, FSB, etc benchmarks. Also many tools like: temp monitor, speed control, etc.
-
23
-
24
Qwen3.6-35B-A3B
Open multimodal model for coding, agents, and long-context tasks
Qwen3.6-35B-A3B is an open-weight multimodal model built for real-world coding, agent workflows, and long-context reasoning. It combines a causal language model with a vision encoder, supports text, image, and video inputs, and is optimized for frameworks such as Transformers, vLLM, SGLang, and KTransformers. The model emphasizes stability, responsiveness, and practical developer productivity, with major improvements in agentic coding, frontend generation, and repository-level reasoning. A...
- Previous
- You're on page 1
- Next
