Search Results for author:
Found 10 papers, 5 papers with code
ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning
By incorporating 2D segmentation masks from the SAM and multi-view CLIP embeddings, ReasonGrounder selects Gaussian groups based on object scale, enabling accurate localization through both explicit and implicit language understanding, even in novel, occluded views.
VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation
Recent image-to-video generation methods have demonstrated success in enabling control over one or two visual elements, such as camera motion or object motion.
ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context
Visual storytelling involves generating a sequence of coherent frames from a textual storyline while maintaining consistency in characters and scenes.
Ranked #1 on
Story Visualization
on Pororo
Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT
We propose an Intelligent Director framework, utilizing LENS to generate descriptions for images and video frames and combining ChatGPT to generate coherent captions while recommending appropriate music names.
Vision Transformers: From Semantic Segmentation to Dense Prediction
Extensive experiments show that our methods achieve appealing performance on a variety of dense prediction tasks (e. g., object detection and instance segmentation and semantic segmentation) as well as image classification.
Clustering by the Probability Distributions from Extreme Value Theory
In contrast, the GPD fits the distribution of distance to the centroid exceeding a sufficiently large threshold, leading to a more stable performance of GPD k-means.
NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection
Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes.
Ranked #6 on
Pedestrian Detection
on Caltech
Incrementally Zero-Shot Detection by an Extreme Value Analyzer
However, zero-shot learning models assume that all seen classes should be known beforehand, while incremental learning models cannot recognize unseen classes.
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task.
Ranked #2 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
Extreme Value k-means Clustering
We thus propose a novel algorithm called Extreme Value k-means (EV k-means), including GEV k-means and GPD k-means.
