Search Results for author:
Found 7 papers, 4 papers with code
Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
This paper introduces D\'ej\`a Vu, a video-language query engine that accelerates ViT-based VideoLMs by reusing computations across consecutive frames.
Active Neural 3D Reconstruction with Colorized Surface Voxel-based View Selection
CSV encapsulates the uncertainty of estimated scene appearance (e. g., color uncertainty) and estimated geometric information (e. g., surface).
DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics
Deep neural network (DNN) video analytics is crucial for autonomous systems such as self-driving vehicles, unmanned aerial vehicles (UAVs), and security robots.
Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning
Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards.
CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics
This paper presents CoVA, a novel cascade architecture that splits the cascade computation between compressed domain and pixel domain to address the decoding bottleneck, supporting both temporal and spatial queries.
Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning
Learning in a multi-target environment without prior knowledge about the targets requires a large amount of samples and makes generalization difficult.
End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization
We develop hierarchically quantized efficient embedding representations for similarity-based search and show that this representation provides not only the state of the art performance on the search accuracy but also provides several orders of speed up during inference.
