Search Results for author:
Found 6 papers, 6 papers with code
OMG-Seg: Is One Model Good Enough For All Segmentation?
In this work, we address various segmentation tasks, each traditionally tackled by distinct or partially unified models.
CLIM: Contrastive Language-Image Mosaic for Region Representation
Our experimental results demonstrate that CLIM improves different baseline open-vocabulary object detectors by a large margin on both OV-COCO and OV-LVIS benchmarks.
Ranked #6 on
Open Vocabulary Object Detection
on LVIS v1.0
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions.
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training.
Aligning Bag of Regions for Open-Vocabulary Object Detection
The embeddings of regions in a bag are treated as embeddings of words in a sentence, and they are sent to the text encoder of a VLM to obtain the bag-of-regions embedding, which is learned to be aligned to the corresponding features extracted by a frozen VLM.
Ranked #7 on
Open Vocabulary Object Detection
on MSCOCO
(using extra training data)
Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images
Following the top-down paradigm, we decompose the task into two stages, i. e. person localization and pose estimation.
Ranked #2 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
