Related papers: Extending Information Bottleneck Attribution to Vi…
The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still rely on Transformers, whose quadratic complexity makes…
Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical,…
In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable…
With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated by rapidly evolving image generation…
Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…
Video learning is an important task in computer vision and has experienced increasing interest over the recent years. Since even a small amount of videos easily comprises several million frames, methods that do not rely on a frame-level…
Instruction-based video editing aims to modify an input video according to a natural-language instruction while preserving content fidelity and temporal coherence. However, existing diffusion-based approaches are often trained on paired…
Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge…
The Information Bottleneck (IB) method (\cite{tishby2000information}) provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective $I(X;Z)-\beta I(Y;Z)$ employs a…
The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of…
Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making. Multiple instance learning with attention pooling provides instance-level explainability, however for many clinical applications a deeper,…
Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance, often characterized by distinct feature sets or descriptive metadata.…
Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person's expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…
Video mirror detection has received significant research attention, yet existing methods suffer from limited performance and robustness. These approaches often over-rely on single, unreliable dynamic features, and are typically built on…
One of the most exciting applications of vision models involve pixel-level reasoning. Despite the abundance of vision foundation models, we still lack representations that effectively embed spatio-temporal properties of visual scenes at the…
Markov processes are widely used mathematical models for describing dynamic systems in various fields. However, accurately simulating large-scale systems at long time scales is computationally expensive due to the short time steps required…
This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data…
Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…
VADMamba pioneered the introduction of Mamba to Video Anomaly Detection (VAD), achieving high accuracy and fast inference through hybrid proxy tasks. Nevertheless, its heavy reliance on optical flow as auxiliary input and inter-task fusion…