6 papers
Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval
Chunxu Liu, Jiyuan Yang, Ruopeng Gao +4
Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent…
On the Suitability of Reinforcement Fine-Tuning to Visual Tasks
Xiaxu Chen, Wei Li, Chunxu Liu +5
Reinforcement Fine-Tuning (RFT) is proved to be greatly valuable for enhancing the reasoning ability of LLMs. Researchers have been starting to apply RFT to MLLMs, hoping it will a…
SORCE: Small Object Retrieval in Complex Environments
Chunxu Liu, Chi Xie, Xiaxu Chen +4
Text-to-Image Retrieval (T2IR) is a highly valuable task that aims to match a given textual query to images in a gallery. Existing benchmarks primarily focus on textual queries des…
History-Aware Transformation of ReID Features for Multiple Object Tracking
Ruopeng Gao, Yuyao Wang, Chunxu Liu +1
In Multiple Object Tracking (MOT), Re-identification (ReID) features are widely employed as a powerful cue for object association. However, they are often wielded as a one-size-fit…
VFIMamba: Video Frame Interpolation with State Space Models
Guozhen Zhang, Chunxu Liu, Yutao Cui +3
Inter-frame modeling is pivotal in generating intermediate frames for video frame interpolation (VFI). Current approaches predominantly rely on convolution or attention-based model…
Sparse Global Matching for Video Frame Interpolation with Large Motion
Chunxu Liu, Guozhen Zhang, Rui Zhao +1
Large motion poses a critical challenge in Video Frame Interpolation (VFI) task. Existing methods are often constrained by limited receptive fields, resulting in sub-optimal perfor…