[ICLR 2026] Official implementation of "Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation"
☆36Jan 26, 2026Updated 7 months ago
Alternatives and similar repositories for DecAF
Users that are interested in DecAF are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICCV 2025] Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs☆62Feb 2, 2026Updated 7 months ago
- Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging☆16Dec 31, 2024Updated last year
- [WACV-2025] Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization☆19May 28, 2025Updated last year
- [ICCV2025] ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors☆60May 17, 2026Updated 4 months ago
- [ICCV'25] CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy☆28Jun 22, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICCV 2025] CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images☆57Jul 15, 2025Updated last year
- Representing 3D Shapes with 64 Latent Vectors for 3D Diffusion Models☆30Sep 15, 2025Updated last year
- [ECCV 2024] VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement☆39Jul 29, 2024Updated 2 years ago
- Official Code for the paper "HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling"☆19Apr 30, 2026Updated 4 months ago
- [AAAI 2026] 4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction☆32Jan 15, 2026Updated 8 months ago
- [CoRL 2025] UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations☆91Dec 18, 2025Updated 9 months ago
- [CVPR 2026 Findings] SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes☆95Nov 25, 2025Updated 9 months ago
- Official PyTorch Implementation of the Paper "Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models"☆23Apr 24, 2025Updated last year
- [ECCV 2024] Official PyTorch implementation of "Classification Matters: Improving Video Action Detection with Class-Specific Attention"☆19Nov 8, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Official Code for the paper "UniversalVTG: A Univeral and Lightweight Foundation Model for Video Temporal Grounding"☆19Apr 15, 2026Updated 5 months ago
- Official code of Veason-R1☆17Jul 14, 2026Updated 2 months ago
- [CVPR 2024] Guided Slot Attention for Unsupervised Video Object Segmentation☆66Dec 23, 2024Updated last year
- DisTime: Distribution-based Time Representation for Video Large Language Models.☆22Jul 10, 2025Updated last year
- [CVPRW 2025] SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields☆25Mar 17, 2024Updated 2 years ago
- (ICML 2026) Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search☆50Aug 7, 2026Updated last month
- [CVPR 2025] CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images☆47Nov 25, 2025Updated 9 months ago
- [ICCVW 2025] TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection☆15Oct 22, 2025Updated 10 months ago
- [CVPR 2024] Context-Guided Spatio-Temporal Video Grounding☆66Jun 28, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 🔮 UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning (NeurIPS 2025)☆254Jan 4, 2026Updated 8 months ago
- [CVPR 2026] Accelerating Streaming Video Large Language Models via Hierarchical Token Compression☆77Jun 8, 2026Updated 3 months ago
- [CVPR'24] Official repo of "Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing"☆20Jul 3, 2025Updated last year
- [DATE 2023] Pipe-BD: Pipelined Parallel Blockwise Distillation☆12Jul 13, 2023Updated 3 years ago
- [NeurIPS 25] InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding☆24Jan 25, 2026Updated 7 months ago
- [CVPR 2026] Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding☆33Apr 12, 2026Updated 5 months ago
- Bayesian Optimization Meets Self-Distillation, ICCV 2023☆10Aug 28, 2023Updated 3 years ago
- This repository contains the implementation of FAPM (2023 ICASSP).☆26Aug 29, 2026Updated 3 weeks ago
- ☆57Sep 13, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos☆26Jun 20, 2026Updated 2 months ago
- [ AAAI 2026 ] The official implementation of 'MonoCLUE: Object-Aware Clustering Enhances Monocular 3D Object Detection'☆22Mar 23, 2026Updated 5 months ago
- Implementation of Learning Instance-Aware Object Detection Using Determinantal Point Processes [https://arxiv.org/pdf/1805.10765.pdf]☆19Nov 21, 2023Updated 2 years ago
- VITA: Video Instance Segmentation via Object Token Association (NeurIPS 2022)☆109Jan 4, 2024Updated 2 years ago
- CVPR2022:Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency☆18Aug 10, 2022Updated 4 years ago
- V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models☆34Apr 16, 2026Updated 5 months ago
- [NeurIPS 2023] The official implementation of SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation☆33Mar 16, 2024Updated 2 years ago