← Search

Bo Ji

14 accepted papers

2026

EyeCue: Driver Cognitive Distraction Detection via Gaze-Empowered Egocentric Video Understanding

IJCAI 2026

Driver cognitive distraction is a major cause of road collisions and remains difficult to detect. Unlike manual or visual distraction, cognitive distraction is diverted by thoughts unrelated to driving, even when the driver appears visually attentive and exhibits no explicit physical movements. In t

Cited by 0Scholar
2025

HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection

AAAI 2025technical

The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it doe…

Cited by 4SourcePDFScholar
2025

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models

AAAI 2025technical

High-resolution Vision-Language Models (VLMs) are widely used in multimodal tasks to enhance accuracy by preserving detailed image information. However, these models often generate an excessive number of visual tokens due to the need to encode multiple partitions of a high-resolution image input. Pr…

2024

Learning-Augmented Online Algorithm for Two-Level Ski-Rental Problem

AAAI 2024technical

In this paper, we study the two-level ski-rental problem, where a user needs to fulfill a sequence of demands for multiple items by choosing one of the three payment options: paying for the on-demand usage (i.e., rent), buying individual items (i.e., single purchase), and buying all the items (i.e.,…

2024

Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting

NeurIPS 2024poster

In this paper, we study the multi-armed bandit problem in the best-of-both-worlds (BOBW) setting with heavy-tailed losses, where the losses can be negative and unbounded but have $(1+v)$-th raw moments bounded by $u^{1+v}$ for some known $u>0$ and $v\in(0,1]$. Specifically, we consider the BOBW sett…

Cited by 0SourcePDFScholar
2022

Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution

ECCV 2022poster

"In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that successfully balance the trade-off rely on fusing results from separa…

2021

Only Train Once: A One-Shot Neural Network Training And Pruning Framework

NeurIPS 2021poster

Structured pruning is a commonly used technique in deploying deep neural networks (DNNs) onto resource-constrained devices. However, the existing pruning methods are usually heuristic, task-specified, and require an extra fine-tuning procedure. To overcome these limitations, we propose a framework t…