activity
20242026
most citedFewer yet critical: Reducing Redundant Token Dependencies for Transformer-based Time Series Forecasting

1 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2025

Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation

Jingyao Wang, Jianqi Zhang, Wenwen Qiang +1

Despite the strength of the Segment Anything Model (SAM), it struggles with generalization issues in open-vocabulary multi-entity segmentation (OVMS). Through empirical and causal…

cs.CV2024

Less yet robust: crucial region selection for scene recognition

Jianqi Zhang, Mengxuan Wang, Jingyao Wang +3

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on co…