Semantic understanding for contextual in-video advertising
Rishi Madhok, Shashank Mujumdar, et al.
AAAI 2018
We propose a novel concept of Deep Part Embeddings (DPEs), which can be used to learn new Convolutional Neural Networks (CNNs) for different classes. We define DPE as a neuron of a trained CNN along with its network of filter activations that is interpretable as a part of a class that the neuron contributes to. Given a new class mathcal{C}, we explore the idea of combining different DPEs that intuitively constitute mathcal{C}, from trained CNNs (not on mathcal{C}), into a network that learns the class mathcal{C} with few training samples. An important application of our proposed framework is the ability to modify a CNN trained on n classes to learn a new class with limited training data without significantly affecting its performance on the n classes. We visually illustrate the different network architectures and extensively evaluate their performance against the baselines.
Rishi Madhok, Shashank Mujumdar, et al.
AAAI 2018
David Haws, Xiaodong Cui
ICASSP 2019
Nishtha Madaan, Shashank Mujumdar, et al.
SCC 2018
Jayachandu Bandlamudi, Kushal Mukherjee, et al.
IAAI 2023