Learning open-world object proposals without learning to classify
Object proposals have become an integral pre-processing step of many vision pipelines
including object detection, weakly supervised detection, object discovery, tracking, etc …
including object detection, weakly supervised detection, object discovery, tracking, etc …
Cotdet: Affordance knowledge prompting for task driven object detection
Task driven object detection aims to detect object instances suitable for affording a task in an
image. Its challenge lies in object categories available for the task being too diverse to be …
image. Its challenge lies in object categories available for the task being too diverse to be …
Transfer learning with deep recurrent neural networks for remaining useful life estimation
Prognostics, such as remaining useful life (RUL) prediction, is a crucial task in condition-
based maintenance. A major challenge in data-driven prognostics is the difficulty of …
based maintenance. A major challenge in data-driven prognostics is the difficulty of …
Iotdefender: A federated transfer learning intrusion detection framework for 5g iot
Y Fan, Y Li, M Zhan, H Cui… - 2020 IEEE 14th …, 2020 - ieeexplore.ieee.org
5G and edge computing promote the development of Internet of Things (IoT). In the near
future, 5G will be used as infrastructure to connect all walks of life. At the same time …
future, 5G will be used as infrastructure to connect all walks of life. At the same time …
Envisioning narrative intelligence: A creative visual storytelling anthology
In this paper, we collect an anthology of 100 visual stories from authors who participated in
our systematic creative process of improvised story-building based on image sequences …
our systematic creative process of improvised story-building based on image sequences …
Learning visual commonsense for robust scene graph generation
Scene graph generation models understand the scene through object and predicate
recognition, but are prone to mistakes due to the challenges of perception in the wild …
recognition, but are prone to mistakes due to the challenges of perception in the wild …
Spatial relationship recognition via heterogeneous representation: A review
Y Wang, H Peng, Y **ong, H Song - Neurocomputing, 2023 - Elsevier
Spatial relationship between objects in an image can help to gain a deep understanding of
the image. At present, spatial relationship recognition has received more and more …
the image. At present, spatial relationship recognition has received more and more …
Human-robot collaboration with commonsense reasoning in smart manufacturing contexts
Human-robot collaboration (HRC), where humans and robots work together to handle
specific tasks, requires designing robots that can effectively support human beings. Robots …
specific tasks, requires designing robots that can effectively support human beings. Robots …
Large model based referring camouflaged object detection
Referring camouflaged object detection (Ref-COD) is a recently-proposed problem aiming to
segment out specified camouflaged objects matched with a textual or visual reference. This …
segment out specified camouflaged objects matched with a textual or visual reference. This …
Cyclic self-training with proposal weight modulation for cross-supervised object detection
Weakly-supervised object detection (WSOD), which requires only image-level annotations
for training detectors, has gained enormous attention. Despite recent rapid advance in …
for training detectors, has gained enormous attention. Despite recent rapid advance in …