Search Results for author:
Found 25 papers, 12 papers with code
Dual-task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding
The retrieval branch uses inter-video contrastive learning to roughly align the global features of paragraphs and videos, reducing modality differences and constructing a coarse-grained feature space to break free from the need for correspondence between paragraphs and videos.
Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding
In addition, a corresponding target object position progressive correction strategy is defined based on the hierarchical matching mechanism to achieve accurate positioning for the target object described in the text.
Hi-GMAE: Hierarchical Graph Masked Autoencoders
To ensure masking uniformity of subgraphs across these scales, we propose a novel coarse-to-fine strategy that initiates masking at the coarsest scale and progressively back-projects the mask to the finer scales.
Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID
Thus, we propose a novel method that uses MLLMs to caption images according to various templates.
Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
To this end, we introduce a novel structure-guided masking strategy (i. e., StructMAE), designed to refine the existing GMAE models.
Single-Image HDR Reconstruction Assisted Ghost Suppression and Detail Preservation Network for Multi-Exposure HDR Imaging
This network, comprising single-frame HDR reconstruction with enhanced stop image (SHDR-ESI) and SHDR-ESI-assisted multi-exposure HDR reconstruction (SHDRA-MHDR), effectively leverages the ghost-free characteristic of single-frame HDR reconstruction and the detail-enhancing capability of ESI in oversaturated areas.
Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning
The experimental results on popular LLMs, such as GPT-3. 5-turbo and Gemini-pro, show that our IR method enhances the overall accuracy of factual reasoning by 27. 33% and mathematical proof by 31. 43%, when compared with traditional DR methods.
CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification
Additionally, acknowledging the complementary nature of semantic details across different modalities, we integrate text features from the bimodal language descriptions to achieve comprehensive semantics.
Exploring Sparsity in Graph Transformers
Graph Transformers (GTs) have achieved impressive results on various graph-related tasks.
Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals.
SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification
The "splice" in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias; 2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together.
Chasing Consistency in Text-to-3D Generation from a Single Image
In light of the above issues, we present Consist3D, a three-stage framework Chasing for semantic-, geometric-, and saturation-Consistent Text-to-3D generation from a single image, in which the first two stages aim to learn parameterized consistency tokens, and the last stage is for optimization.
Progressive Feature Mining and External Knowledge-Assisted Text-Pedestrian Image Retrieval
In addition, to further reduce the negative impact of modal discrepancy and text diversity on cross-modal matching, we propose to use other sample knowledge of the same modality, i. e., external knowledge to enhance identity-consistent features and weaken identity-inconsistent features.
Prototype-Driven and Multi-Expert Integrated Multi-Modal MR Brain Tumor Image Segmentation
To this end, a multi-modal MR brain tumor segmentation method with tumor prototype-driven and multi-expert integration is proposed.
Free-Form Composition Networks for Egocentric Action Recognition
We evaluated our method on three popular egocentric action recognition datasets, Something-Something V2, H2O, and EPIC-KITCHENS-100, and the experimental results demonstrate the effectiveness of the proposed method for handling data scarcity problems, including long-tailed and few-shot egocentric action recognition.
Adversarial Self-Attack Defense and Spatial-Temporal Relation Mining for Visible-Infrared Video Person Re-Identification
In this work, the changes of views, posture, background and modal discrepancy are considered as the main factors that cause the perturbations of person identity features.
Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks
However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where significant redundancy exists.
Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples
Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain.
Hetero-Center Loss for Cross-Modality Person Re-Identification
With the joint supervision of Cross-Entropy (CE) loss and HC loss, the network is trained to achieve two vital objectives, inter-class discrepancy and intra-class cross-modality similarity as much as possible.
Cross-Modality Person Re-identification
Person Re-Identification
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations.
Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
In this paper, we investigate a novel deep-model reusing task.
Semantic Adversarial Network with Multi-scale Pyramid Attention for Video Classification
Two-stream architecture have shown strong performance in video classification task.
Ensemble p-Laplacian Regularization for Remote Sensing Image Recognition
Therefore, we develop an ensemble p-Laplacian regularization (EpLapR) to fully approximate the intrinsic manifold of the data distribution.
Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks
Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible.
Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition
Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition.
