Search Results for author:
Found 33 papers, 22 papers with code
SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations.
Accelerating Diffusion Transformer via Error-Optimized Cache
Existing caching methods accelerate generation by reusing DiT features from the previous time step and skipping calculations in the next, but they tend to locate and cache low-error modules without focusing on reducing caching-induced errors, resulting in a sharp decline in generated content quality when increasing caching intensity.
CookingDiffusion: Cooking Procedural Image Generation with Stable Diffusion
These prompts encompass text prompts (representing cooking steps), image prompts (corresponding to cooking images), and multi-modal prompts (mixing cooking steps and images), ensuring the consistent generation of cooking procedural images.
Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
The success of text-to-image generation enabled by diffuion models has imposed an urgent need to erase unwanted concepts, e. g., copyrighted, offensive, and unsafe ones, from the pre-trained models in a precise, timely, and low-cost manner.
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions.
Hand1000: Generating Realistic Hands from Text with Only 1,000 Images
The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model's understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation.
Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective
In this paper, we re-examine the SID problem and identify two prevalent biases in current training paradigms, i. e., weakened artifact features and overfitted artifact features.
Selective Vision-Language Subspace Projection for Few-shot CLIP
Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts.
Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation
However, these adaptation methods are usually operated on the global view of an input image, and thus biased perception of partial local details of the image.
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
To alleviate these issues, leveraging on diffusion models' remarkable synthesis capabilities, we propose Diffusion-based Model Inversion (Diff-MI) attacks.
PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition
In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks.
A Sanity Check for AI-generated Image Detection
This effectively enables the model to discern AI-generated images based on semantics or contextual information; Secondly, we select the highest frequency patches and the lowest frequency patches in the image, and compute the low-level patchwise features, aiming to detect AI-generated images by low-level artifacts, for example, noise pattern, anti-aliasing, etc.
Hierarchical Space-Time Attention for Micro-Expression Recognition
Specifically, we first process ME video frames and special frames or data parallelly by our cascaded Unimodal Space-Time Attention (USTA) to establish connections between subtle facial movements and specific facial areas.
Micro Expression Recognition
Micro-Expression Recognition
+1
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications.
Boosting Few-Shot Learning via Attentive Feature Regularization
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor.
A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming
This paper offers an insightful examination of how currently top-trending AI technologies, i. e., generative artificial intelligence (Generative AI) and large language models (LLMs), are reshaping the field of video technology, including video generation, understanding, and streaming.
Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noise
Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques.
Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective
Leveraging on the remarkable capabilities of foundation models (i. e., Llama2 and SAM), we propose to augment recipe and food image by extracting alignable information related to the counterpart.
Selective Volume Mixup for Video Action Recognition
In this paper, we propose a novel video augmentation strategy named Selective Volume Mixup (SV-Mix) to improve the generalization ability of deep models with limited training videos.
CgT-GAN: CLIP-guided Text GAN for Image Captioning
Particularly, we use adversarial training to teach CgT-GAN to mimic the phrases of an external text corpus and CLIP-based reward to provide semantic guidance.
Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation
This study introduces an efficacious approach, Masked Collaborative Contrast (MCC), to highlight semantic regions in weakly supervised semantic segmentation.
Contrastive Learning
Weakly supervised Semantic Segmentation
+1
TKN: Transformer-based Keypoint Prediction Network For Real-time Video Prediction
Video prediction is a complex time-series forecasting task with great potential in many use cases.
Bi-directional Distribution Alignment for Transductive Zero-Shot Learning
It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not match.
3D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention
On this basis, we devise STCFormer by stacking multiple STC blocks and further integrate a new Structure-enhanced Positional Embedding (SPE) into STCFormer to take the structure of human body into consideration.
Ranked #8 on
3D Human Pose Estimation
on MPI-INF-3DHP
Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP
They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers.
Long-term Leap Attention, Short-term Periodic Shift for Video Classification
By replacing a vanilla 2D attention with the LAPS, we could adapt a static transformer into a video one, with zero extra parameters and neglectable computation overhead ($\sim$2. 6\%).
Attention in Attention: Modeling Context Correlation for Efficient Video Classification
Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts.
Group Contextualization for Video Recognition
By utilizing calibrators to embed feature with four different kinds of contexts in parallel, the learnt representation is expected to be more resilient to diverse types of activities.
Ranked #3 on
Egocentric Activity Recognition
on EGTEA
Token Shift Transformer for Video Classification
It is worth noticing that our TokShift transformer is a pure convolutional-free video transformer pilot with computational efficiency for video understanding.
Aggregated Multi-GANs for Controlled 3D Human Motion Prediction
Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways.
Motion Prediction Using Trajectory Cues
Predicting human motion from a historical pose sequence is at the core of many applications in computer vision.
Cross-sentence Pre-trained Model for Interactive QA matching
In addition to the context information captured at each word position, we incorporate a new quantity of context information jump to facilitate the attention weight formulation.
