1 citations · 1 across the 6 of their papers we have counts for
3 papers · 1 filter
Dual-Signal Adaptive KV-Cache Optimization for Long-Form Video Understanding in Vision-Language Models
Vishnu Sai, Dheeraj Sai, Srinath B +2
Vision-Language Models (VLMs) face a critical memory bottleneck when processing long-form video content due to the linear growth of the Key-Value (KV) cache with sequence length. E…
ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions
Furqan Ahmed Shaik, Sandeep Nagar, Aiswarya Maturi +7
The ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions served as a rigorous platform to evaluate and benchmark state-…
IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather
Furqan Ahmed Shaik, Abhishek Malreddy, Nikhil Reddy Billa +3
Large-scale deployment of fully autonomous vehicles requires a very high degree of robustness to unstructured traffic, and weather conditions, and should prevent unsafe mispredicti…