10 citations · 23 across the 18 of their papers we have counts for
18 papers
Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMs
Afsara Benazir, Chen Chen, Rongxiao Qu +3
Mixture-of-Experts (MoE) LLMs scale model capacity efficiently through sparse activation, but their large expert parameter footprint, routing imbalance, and long-context KV-cache g…
Argus-Unified: Towards A Compact and Economical Unified Model for Image Understanding and Generation
Weiming Zhuang, Jiabo Huang, Jingtao Li +4
Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data demands and conflicts between t…
Empirical Recipes for Efficient and Compact Vision-Language Models
Jiabo Huang, Zhizhong Li, Sina Sajadmanesh +2
Deploying vision-language models (VLMs) in resource-constrained settings demands low latency and high throughput, yet existing compact VLMs often fall short of the inference speedu…
UniCompress: Token Compression for Unified Vision-Language Understanding and Generation
Ziyao Wang, Chen Chen, Jingtao Li +4
Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework.…
Neuro-Symbolic Spatial Reasoning in Segmentation
Jiayi Lin, Jiabo Huang, Shaogang Gong
Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of categories, requiring generalization to unseen and unlabelled objects. Using vision-lang…
Seeing Further on the Shoulders of Giants: Knowledge Inheritance for Vision Foundation Models
Jiabo Huang, Chen Chen, Lingjuan Lyu
Vision foundation models (VFMs) are predominantly developed using data-centric methods. These methods require training on vast amounts of data usually with high-quality labels, whi…
UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models
Yimu Wang, Weiming Zhuang, Chen Chen +3
In the era of deep learning, the increasing number of pre-trained models available online presents a wealth of knowledge. These models, developed with diverse architectures and tra…
InvSeg: Test-Time Prompt Inversion for Semantic Segmentation
Jiayi Lin, Jiabo Huang, Jian Hu +1
Visual-textual correlations in the attention maps derived from text-to-image diffusion models are proven beneficial to dense visual prediction tasks, e.g., semantic segmentation. H…
MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval
Weitong Cai, Jiabo Huang, Shaogang Gong +2
Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequa…
Hybrid-Learning Video Moment Retrieval across Multi-Domain Labels
Weitong Cai, Jiabo Huang, Shaogang Gong
Video moment retrieval (VMR) is to search for a visual temporal moment in an untrimmed raw video by a given text query description (sentence). Existing studies either start from co…
Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval
Dezhao Luo, Shaogang Gong, Jiabo Huang +2
Video moment retrieval (VMR) aims to locate the most likely video moment(s) corresponding to a text query in untrimmed videos. Training of existing methods is limited by the lack o…
Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models
Dezhao Luo, Jiabo Huang, Shaogang Gong +2
Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are lik…
Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training
Dezhao Luo, Jiabo Huang, Shaogang Gong +2
The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for vi…
Video Activity Localisation with Uncertainties in Temporal Boundary
Jiabo Huang, Hailin Jin, Shaogang Gong +1
Current methods for video activity localisation over time assume implicitly that activity temporal boundaries labelled for model training are determined and precise. However, in un…
Feature-Distribution Perturbation and Calibration for Generalized Person ReID
Qilei Li, Jiabo Huang, Jian Hu +1
Person Re-identification (ReID) has been advanced remarkably over the last 10 years along with the rapid development of deep learning for visual recognition. However, the i.i.d. (i…
Local-Global Associative Frame Assemble in Video Re-ID
Qilei Li, Jiabo Huang, Shaogang Gong
Noisy and unrepresentative frames in automatically generated object bounding boxes from video sequences cause significant challenges in learning discriminative representations in v…
Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation
Jiabo Huang, Yang Liu, Shaogang Gong +1
Video activity localisation has recently attained increasing attention due to its practical values in automatically localising the most salient visual segments corresponding to the…
Deep Clustering by Semantic Contrastive Learning
Jiabo Huang, Shaogang Gong
Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential…