Search Results for author:
Found 16 papers, 5 papers with code
Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
Specifically, the instruction condition is injected into the grouped visual tokens at the local level and the learnable tokens at the global level, and we conduct the attention mechanism to complete the conditional compression.
Rethinking Video Tokenization: A Conditioned Diffusion-based Approach
Trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch, extensive experiments demonstrate that CDT achieves state-of-the-art performance in video reconstruction tasks with just a single-step sampling.
ContextHOI: Spatial Context Learning for Human-Object Interaction Detection
To enhance the capabilities of object detectors for HOI detection, we present a dual-branch framework named ContextHOI, which efficiently captures both object detection features and spatial contexts.
Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection
Human-object interaction (HOI) detectors with popular query-transformer architecture have achieved promising performance.
Improved Video VAE for Latent Video Diffusion Model
Specifically, the KTC architecture divides the latent space into two branches, in which one half completely inherits the compression prior of keyframes from a lower-dimension image VAE while the other half involves temporal compression through 3D group causal convolution, reducing temporal-spatial conflicts and accelerating the convergence speed of video VAE.
Learning Restricted Boltzmann Machines with greedy quantum search
Restricted Boltzmann Machines (RBMs) are widely used probabilistic undirected graphical models with visible and latent nodes, playing an important role in statistics and machine learning.
Provable learning of quantum states with graphical models
Several works consider subclasses of quantum states that can be learned in polynomial sample complexity such as stabilizer states or high-temperature Gibbs states.
MomentDiff: Generative Video Moment Retrieval from Random to Real
Video moment retrieval pursues an efficient and generalized solution to identify the specific temporal segments within an untrimmed video that correspond to a given language description.
Weakly Supervised Learning with Side Information for Noisy Labeled Images
In many real-world datasets, like WebVision, the performance of DNN based classifier is often limited by the noisy labeled data.
Variational Quantum Circuit Model for Knowledge Graphs Embedding
In this work, we propose the first quantum Ans\"atze for the statistical relational learning on knowledge graphs using parametric quantum circuits.
Geometry-Aware Scene Text Detection With Instance Transformation Network
Localizing text in the wild is challenging in the situations of complicated geometric layout of the targets like random orientation and large aspect ratio.
Deeply-Learned Part-Aligned Representations for Person Re-Identification
In this paper, we address the problem of person re-identification, which refers to associating the persons captured from different cameras.
Ranked #112 on
Person Re-Identification
on Market-1501
Deep Convolutional Neural Networks with Merge-and-Run Mappings
A deep residual network, built by stacking a sequence of residual blocks, is easy to train, because identity mappings skip residual branches and thus improve information flow.
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner.
Metric Learning Driven Multi-Task Structured Output Optimization for Robust Keypoint Tracking
As an important and challenging problem in computer vision and graphics, keypoint-based object tracking is typically formulated in a spatio-temporal statistical learning framework.
