Media Summary: In this paper, we propose DetCLIPv2, an efficient and scalable end-to-end training framework that incorporates large-scale ... Alireza Zareian, Kevin Dela Rosa, Derek Hao Hu, Shih-Fu Chang; Proceedings of the IEEE/CVF Conference on Computer Vision ... IEEE/CVF Conference on Computer Vision and Pattern

Open Vocabulary Attribute Detection Cvpr - Detailed Analysis & Overview

In this paper, we propose DetCLIPv2, an efficient and scalable end-to-end training framework that incorporates large-scale ... Alireza Zareian, Kevin Dela Rosa, Derek Hao Hu, Shih-Fu Chang; Proceedings of the IEEE/CVF Conference on Computer Vision ... IEEE/CVF Conference on Computer Vision and Pattern

Photo Gallery

Open-Vocabulary Attribute Detection (CVPR 2023)
CVPR2023 OvarNet: Towards Open-vocabulary Object Attribute Recognition
Open-vocabulary object 6D pose estimation - CVPR 2024
CVPR 2025: Compositional Caching for Training-free Open-vocabulary Attribute Detection
[CVPR 2024] Evaluating open-vocabulary object detectors for fine-grained understanding
[CVPR23] DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment
Teach AI to See Details - COMCA: Detecting Visual Attributes Without Training (CVPR) 🕵️‍♂️🖼️
Compositional Caching for Training-free Open-vocabulary Attribute Detection
[CVPR 2024] YOLO-World: Real-Time Open-Vocabulary Object Detection
[CVPR 2024] Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation
Open-Vocabulary Object Detection Using Captions (CVPR'21 Oral)
[CVPR'24] Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection
Sponsored
Sponsored
View Detailed Profile
Open-Vocabulary Attribute Detection (CVPR 2023)

Open-Vocabulary Attribute Detection (CVPR 2023)

Short video presentation of our paper "

CVPR2023 OvarNet: Towards Open-vocabulary Object Attribute Recognition

CVPR2023 OvarNet: Towards Open-vocabulary Object Attribute Recognition

CVPR2023 | OvarNet: Towards

Sponsored
Open-vocabulary object 6D pose estimation - CVPR 2024

Open-vocabulary object 6D pose estimation - CVPR 2024

We introduce the new setting of

CVPR 2025: Compositional Caching for Training-free Open-vocabulary Attribute Detection

CVPR 2025: Compositional Caching for Training-free Open-vocabulary Attribute Detection

CVPR

[CVPR 2024] Evaluating open-vocabulary object detectors for fine-grained understanding

[CVPR 2024] Evaluating open-vocabulary object detectors for fine-grained understanding

Short overview of our

Sponsored
[CVPR23] DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

[CVPR23] DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

In this paper, we propose DetCLIPv2, an efficient and scalable end-to-end training framework that incorporates large-scale ...

Teach AI to See Details - COMCA: Detecting Visual Attributes Without Training (CVPR) 🕵️‍♂️🖼️

Teach AI to See Details - COMCA: Detecting Visual Attributes Without Training (CVPR) 🕵️‍♂️🖼️

"

Compositional Caching for Training-free Open-vocabulary Attribute Detection

Compositional Caching for Training-free Open-vocabulary Attribute Detection

Compositional Caching for Training-free

[CVPR 2024] YOLO-World: Real-Time Open-Vocabulary Object Detection

[CVPR 2024] YOLO-World: Real-Time Open-Vocabulary Object Detection

YOLO-World is the cutting-edge model for

[CVPR 2024] Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation

[CVPR 2024] Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation

Welcome to our presentation on "

Open-Vocabulary Object Detection Using Captions (CVPR'21 Oral)

Open-Vocabulary Object Detection Using Captions (CVPR'21 Oral)

Alireza Zareian, Kevin Dela Rosa, Derek Hao Hu, Shih-Fu Chang; Proceedings of the IEEE/CVF Conference on Computer Vision ...

[CVPR'24] Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection

[CVPR'24] Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection

IEEE/CVF Conference on Computer Vision and Pattern

CVPR 2026 | Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection

CVPR 2026 | Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection

This video presents our