Related papers: Fast-OMRA: Fast Online Motion Resolution Adaptatio…
In this paper, we introduce a collaborative training algorithm of balanced random forests with convolutional neural networks for domain adaptation tasks. In real scenarios, most domain adaptation algorithms face the challenges from noisy,…
The cross-media retrieval problem has received much attention in recent years due to the rapid increasing of multimedia data on the Internet. A new approach to the problem has been raised which intends to match features of different…
Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal…
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning…
We study learning object segmentation from unlabeled videos. Humans can easily segment moving objects without knowing what they are. The Gestalt law of common fate, i.e., what move at the same speed belong together, has inspired…
Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically…
Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…
Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory…
Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train…
Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the…
This paper introduces a dual-critic reinforcement learning (RL) framework to address the problem of frame-level bit allocation in HEVC/H.265. The objective is to minimize the distortion of a group of pictures (GOP) under a rate constraint.…
We propose an application of online hard sample mining for efficient training of Neural Radiance Fields (NeRF). NeRF models produce state-of-the-art quality for many 3D reconstruction and rendering tasks but require substantial…
Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain. In medical image segmentation field, most existing UDA methods depend on adversarial learning to address the…
In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual…
Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the…
Large pre-trained vision-language models like CLIP have transformed computer vision by aligning images and text in a shared feature space, enabling robust zero-shot transfer via prompting. Soft-prompting, such as Context Optimization…
With the rapid evolution of the Internet of Things, many real-world applications utilize heterogeneously connected sensors to capture time-series information. Edge-based machine learning (ML) methodologies are often employed to analyze…
Conventional video compression methods employ a linear transform and block motion model, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to combinatorial…
Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due…
Estimation of pain intensity from facial expressions captured in videos has an immense potential for health care applications. Given the challenges related to subjective variations of facial expressions, and operational capture conditions,…