Search Results for author:
Found 28 papers, 17 papers with code
Exploring Interpretability for Visual Prompt Tuning with Hierarchical Concepts
Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks.
FaceShot: Bring Any Character into Life
With this powerful generalization capability, FaceShot can significantly extend the application of portrait animation by breaking the limitation of realistic portrait landmark detection for any stylized character and driven video.
DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation.
Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection
We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains.
HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling
Specifically, we introduce a relationship-guided attention module to capture pair-wise associations among entities and attributes for low-level prompt learning.
Ranked #1 on
Prompt Engineering
on ImageNet V2
ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding
Video temporal grounding is an emerging topic aiming to identify specific clips within videos.
StyleShot: A Snapshot on Any Style
In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning.
Ranked #1 on
Style Transfer
on StyleBench
DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-World
Consequently, DiffPhysBA can generate realistic attributes as semantic-level triggers in the digital domain and provides higher physical ASR compared to the direct paste method by 25. 6% on the real-world test set.
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance.
PatSTEG: Modeling Formation Dynamics of Patent Citation Networks via The Semantic-Topological Evolutionary Graph
Patent documents in the patent database (PatDB) are crucial for research, development, and innovation as they contain valuable technical information.
DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification
Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, or relying on semantic information for attention guidance, DROP argues that the inferior performance of the former is due to distinct granularity requirements for ReID and human parsing features.
Ranked #4 on
Person Re-Identification
on Occluded-DukeMTMC
Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models
To address this limitation and prioritize harnessing structured knowledge, this paper advocates for leveraging LLMs to build a graph for each description to model the entities and attributes describing the category, as well as their correlations.
Ranked #2 on
Prompt Engineering
on ImageNet V2
Online Video Quality Enhancement with Spatial-Temporal Look-up Tables
To the best of our knowledge, we are the first to exploit the LUT structure to extract temporal information in video tasks.
Content-Adaptive Auto-Occlusion Network for Occluded Person Re-Identification
To address these challenges, we propose a novel Content-Adaptive Auto-Occlusion Network (CAAO), that is able to dynamically select the proper occlusion region of an image based on its content and the current training status.
Explainability of Speech Recognition Transformers via Gradient-based Attention Visualization
In addition, we demonstrate the utilization of visualization result in three ways: (1) We visualize attention with respect to connectionist temporal classification (CTC) loss to train an ASR model with adversarial attention erasing regularization, which effectively decreases the word error rate (WER) of the model and improves its generalization capability.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
ISTVT: Interpretable Spatial-Temporal Video Transformer for Deepfake Detection
To address these two challenges, in this paper, we propose an Interpretable Spatial-Temporal Video Transformer (ISTVT), which consists of a novel decomposed spatial-temporal self-attention and a self-subtract mechanism to capture spatial artifacts and temporal inconsistency for robust Deepfake detection.
Human Co-Parsing Guided Alignment for Occluded Person Re-identification
Most supervised methods propose to train an extra human parsing model aside from the ReID model with cross-domain human parts annotation, suffering from expensive annotation cost and domain gap; Unsupervised methods integrate a feature clustering-based human parsing process into the ReID model, but lacking supervision signals brings less satisfactory segmentation results.
Ranked #9 on
Person Re-Identification
on Occluded-DukeMTMC
Learning Domain Invariant Prompt for Vision-Language Models
Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples.
Ranked #5 on
Prompt Engineering
on Food-101
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification
Instead of learning fixed triggers for the target classes from the training set, DT-IBA can dynamically generate new triggers for any unknown identities.
Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling
Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set.
Towards Privacy-Preserving Person Re-identification via Person Identify Shift
In this paper, we aim to develop a technique that can achieve a good trade-off between privacy protection and data usability for person ReID.
Context-Aware Feature Learning for Noise Robust Person Search
For human-introduced noise, we propose a noise-discovery and noise-suppression training process for mislabeling robust person search.
Adaptive Discriminative Regularization for Visual Classification
Regarding this hypothesis, we propose a novel regularization to improve discriminative learning.
Rethinking the Zigzag Flattening for Image Reading
Sequence ordering of word vector matters a lot to text reading, which has been proven in natural language processing (NLP).
Salience-Guided Iterative Asymmetric Mutual Hashing for Fast Person Re-identification
Moreover, a novel iterative asymmetric mutual training strategy (IAMT) is proposed to alleviate drawbacks of common mutual learning, which can continuously refine the discriminative regions for SSB and extract regularized dark knowledge for two models as well.
Improved Instance Discrimination and Feature Compactness for End-to-End Person Search
Our method achieves comparable performance on two benchmarks, CUHK-SYSU and PRW, and achieves 91. 96% of mAP and 93. 34% of rank1 accuracy on CUHK-SYSU.
Incremental Generative Occlusion Adversarial Suppression Network for Person ReID
The adversarial suppression branch, embedded with two occlusion suppression module, minimizes the generated occlusion’s response and strengthens attentive feature representation on human non-occluded body regions.
Ranked #27 on
Person Re-Identification
on Occluded-DukeMTMC
Deep Fusion Feature Representation Learning with Hard Mining Center-Triplet Loss for Person Re-identification
The extraction of robust feature representations from pedestrian images through CNNs with a single deterministic pooling operation is problematic as the features in real pedestrian images are complex and diverse.
