Related papers: Visual Relationship Detection Based on Guided Prop…
Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and…
Since the beginning of early civilizations, social relationships derived from each individual fundamentally form the basis of social structure in our daily life. In the computer vision literature, much progress has been made in scene…
Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world. The VCR task, which calls for exploiting the…
We consider the problem of naming objects in complex, natural scenes containing widely varying object appearance and subtly different names. Informed by cognitive research, we propose an approach based on sharing context based object…
Recommender systems presently utilize vast amounts of data and play a pivotal role in enhancing user experiences. Graph Convolution Networks (GCNs) have surfaced as highly efficient models within the realm of recommender systems due to…
Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects,…
Decades of psychological research have been aimed at modeling how people learn features and categories. The empirical validation of these theories is often based on artificial stimuli with simple representations. Recently, deep neural…
People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique…
A deeper understanding of video activities extends beyond recognition of underlying concepts such as actions and objects: constructing deep semantic representations requires reasoning about the semantic relationships among these concepts,…
Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large variations in human-object configurations, multiple co-occurring…
The words of a language reflect the structure of the human mind, allowing us to transmit thoughts between individuals. However, language can represent only a subset of our rich and detailed cognitive architecture. Here, we ask what kinds of…
Weakly supervised phrase grounding aims at learning region-phrase correspondences using only image-sentence pairs. A major challenge thus lies in the missing links between image regions and sentence phrases during training. To address this…
Partial multi-task learning where training examples are annotated for one of the target tasks is a promising idea in remote sensing as it allows combining datasets annotated for different tasks and predicting more tasks with fewer network…
Accurately retrieving images that are semantically similar remains a fundamental challenge in computer vision, as traditional methods often fail to capture the relational and contextual nuances of a scene. We introduce PRISm (Pruning-based…
Knowledge distillation facilitates the training of a compact student network by using a deep teacher one. While this has achieved great success in many tasks, it remains completely unstudied for image-based 6D object pose estimation. In…
Discovering social relations in images can make machines better interpret the behavior of human beings. However, automatically recognizing social relations in images is a challenging task due to the significant gap between the domains of…
Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already…
A structured query can capture the complexity of object interactions (e.g. 'woman rides motorcycle') unlike single objects (e.g. 'woman' or 'motorcycle'). Retrieval using structured queries therefore is much more useful than single object…
We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this problem can significantly reduce the dependence on large-scale…
This work focuses on the semantic relations between scenes and objects for visual object recognition. Semantic knowledge can be a powerful source of information especially in scenarios with few or no annotated training samples. These…