![](https://sigport.org/sites/default/files/styles/list/public/EAPM.png?itok=PHmok32F)
- Read more about Deep Object Detection With Example Attribute Based Prediction Modulation
- Log in to post comments
Deep object detectors suffer from the gradient contribution imbalance during training. In this paper, we point out that such imbalance can be ascribed to the imbalance in example attributes, e.g., difficulty and shape variation degree. We further propose example attribute based prediction modulation (EAPM) to address it. In EAPM, first, the attribute of an example is defined by the prediction and the corresponding ground truth. Then, a modulating factor w.r.t the example attribute is introduced to modulate the prediction error.
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2022_0.jpg?itok=_WnBJxvM)
- Read more about DYNAMIC TEXTURE RECOGNITION USING PDV HASHING AND DICTIONARY LEARNING ON MULTI-SCALE VOLUME LOCAL BINARY PATTERN
- Log in to post comments
Spatial-temporal local binary pattern (STLBP) has been widely used in dynamic texture recognition. STLBP often encounters the high-dimension problem as its dimension increases exponentially, so that STLBP could only utilize a small neighborhood. To tackle this problem, we propose a method for dynamic texture recognition using PDV hashing and dictionary learning on multi-scale volume local binary pattern (PHD-MVLBP).
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2022_0.jpg?itok=_WnBJxvM)
- Read more about SPATIAL-CONTEXT-AWARE DEEP NEURAL NETWORK FOR MULTI-CLASS IMAGE CLASSIFICATION
- Log in to post comments
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2022_0.jpg?itok=_WnBJxvM)
- Read more about VARIATIONAL BAYESIAN FRAMEWORK FOR ADVANCED IMAGE GENERATION WITH DOMAIN-RELATED VARIABLES
- Log in to post comments
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2022_0.jpg?itok=_WnBJxvM)
- Read more about VARIATIONAL BAYESIAN FRAMEWORK FOR ADVANCED IMAGE GENERATION WITH DOMAIN-RELATED VARIABLES
- Log in to post comments
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2022_0.jpg?itok=_WnBJxvM)
- Read more about Model-Based Reconstruction for Collimated Beam Ultrasound Systems
- Log in to post comments
Collimated beam ultrasound systems are a novel technology for imaging inside multi-layered structures such as geothermal wells. Such systems include a transmitter and multiple receivers to capture reflected signals. Common algorithms for ultrasound reconstruction use delay-and-sum (DAS) approaches; these have low computational complexity but produce inaccurate images in the presence of complex structures and specialized geometries such as collimated beams.
ICASSP2022.pdf
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/cover_6.jpg?itok=j9iF0qMF)
- Read more about Adaptive Actor-Critic Bilateral Filter
- Log in to post comments
Recent research on edge-preserving image smoothing has suggested that bilateral filtering is vulnerable to maliciously perturbed filtering input. However, while most prior works analyze the adaptation of the range kernel in one-step manner, in this paper we take a more constructive view towards multi-step framework with the goal of unveiling the vulnerability of bilateral filtering.
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/pipeline_fig.png?itok=vSCaydzV)
- Read more about Video Anomaly Detection via Prediction Network with Enhanced Spatio-temporal Memory Exchange
- Log in to post comments
Video anomaly detection is a challenging task because most anomalies are scarce and non-deterministic. Many approaches investigate the reconstruction difference between normal and abnormal patterns, but neglect that anomalies do not necessarily correspond to large reconstruction errors. To address this issue, we design a Convolutional LSTM Auto-Encoder prediction framework with enhanced spatio-temporal memory exchange using bi-directionalilty and a higher-order mechanism. The bi-directional structure promotes learning the temporal regularity through forward and backward predictions.
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2022_0.jpg?itok=_WnBJxvM)
- Read more about LOOK, LISTEN AND PAY MORE ATTENTION: FUSING MULTI-MODAL INFORMATION FOR VIDEO VIOLENCE DETECTION
- Log in to post comments
Violence detection is an essential and challenging problem in the computer vision community. Most existing works focus on single modal data analysis, which is not effective when multi-modality is available.
- Categories: