Deep reinforcement learning augments the reinforcement learning framework and utilizes
the powerful representation of deep neural networks. Recent works have demonstrated the …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

Image segmentation is the task of associating pixels in an image with their respective object
class labels. It has a wide range of applications in many industries including healthcare …

Abstract Recently, several Space-Time Memory based networks have shown that the object
cues (eg video frames as well as the segmented object masks) from the past frames are …

Fine-grained bird image classification (FBIC) is not only meaningful for endangered bird
observation and protection but also a prevalent task for image classification in multimedia …

Video segmentation—partitioning video frames into multiple segments or objects—plays a
critical role in a broad range of practical applications, from enhancing visual effects in movie …

We present TDNet, a temporally distributed network designed for fast and accurate video
semantic segmentation. We observe that features extracted from a certain high-level layer of …

Recently, memory-based approaches show promising results on semi-supervised video
object segmentation. These methods predict object masks frame-by-frame with the help of …

The contextual information plays a core role in semantic segmentation. As for video
semantic segmentation, the contexts include static contexts and motional contexts …

Affective computing is an emerging area of research that aims to enable intelligent systems
to recognize, feel, infer and interpret human emotions. The widely spread online and off-line …