Unifying two-stream encoders with transformers for cross-modal retrieval
Most existing cross-modal retrieval methods employ two-stream encoders with different
architectures for images and texts, eg, CNN for images and RNN/Transformer for texts. Such …
architectures for images and texts, eg, CNN for images and RNN/Transformer for texts. Such …
Frequency information disentanglement network for video-based person re-identification
Recently, most video-based person re-identification (Re-ID) methods adopt complex model
or multi-scaled information to explore more discriminative spatio-temporal clues, thus …
or multi-scaled information to explore more discriminative spatio-temporal clues, thus …
Hsmh: A hierarchical sequence multi-hop reasoning model with reinforcement learning
The incompleteness of knowledge graphs (KGs) negatively impacts the performance of KGs
in downstream applications (eg, recommendation systems and information retrieval). This …
in downstream applications (eg, recommendation systems and information retrieval). This …
A Mutually Textual and Visual Refinement Network for Image-Text Matching
Image-text matching is vital important in the field of multi-modal intelligence. Recently, it is
advocated in a way that decomposes images and texts into local fragments and followed by …
advocated in a way that decomposes images and texts into local fragments and followed by …
Multimodal Progressive Modulation Network for Micro-video Multi-label Classification
Micro-videos, as an increasingly popular form of user-generated content (UGC), naturally
include diverse multimodal cues. However, in pursuit of consistent representations, existing …
include diverse multimodal cues. However, in pursuit of consistent representations, existing …
Spatial-Channel Attention Transformer with Pseudo Regions for Remote Sensing Image-Text Retrieval
Recently, remote sensing image-text retrieval (RSITR) has received significant attention due
to its flexible query form and effective management of remote sensing images. However …
to its flexible query form and effective management of remote sensing images. However …
ITContrast: contrastive learning with hard negative synthesis for image-text matching
Image-text matching aims to bridge vision and language so as to match the instance of one
modality with the instance of another modality. Recent years have seen considerable …
modality with the instance of another modality. Recent years have seen considerable …