Current attention algorithms (eg, self-attention) are stimulus-driven and highlight all the
salient objects in an image. However, intelligent agents like humans often guide their …

Introducing deep trackers to thermal infrared (TIR) tracking is hampered by the scarcity of
large training datasets. To alleviate the predicament, a common approach is full fine-tuning …

As part of the effort to understand how the brain learns, ongoing research seeks to combine
biological knowledge with current artificial intelligence (AI) modeling in an attempt to find an …

We study the unsupervised representation learning for the semantic segmentation task.
Different from previous works that aim at providing unsupervised pre-trained backbones for …

Convolutional video models have an order of magnitude larger computational complexity
than their counterpart image-level models. Constrained by computational resources, there is …

The computational complexity of video models increases linearly with the square number of
frames. Thus, constrained bycomputational resources, training video models to learn long …

Object part parsing involves segmenting objects into semantic parts, which has drawn great
attention recently. The current methods ignore the specific hierarchical structure of the …

Action recognition research is usually in the single-view setting. But human action is not
single-view based in many cases. A lot of simple action is composed of both body …

As part of understanding how the brain learns, ongoing work seeks to combine biological
knowledge and current artificial intelligence (AI) modeling in an attempt to find an efficient …

The introduction of Transformer networks in computer vision has resulted in rapid progress
of deep models in a variety of vision tasks. These performance gains are strongly tied to the …