Search Results for author:
Found 14 papers, 2 papers with code
Disambiguation of morpho-syntactic features of African American English – the case of habitual be
To overcome the scarcity, we employ a combination of rule-based filters and data augmentation that generate a corpus balanced between habitual and non-habitual instances.
HeiMorph at SIGMORPHON 2022 Shared Task on Morphological Acquisition Trajectories
This paper presents the submission by the HeiMorph team to the SIGMORPHON 2022 task 2 of Morphological Acquisition Trajectories.
GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning
This paper investigates the ethical implications of aligning Large Language Models (LLMs) with financial optimization, through the case study of GreedLlama, a model fine-tuned to prioritize economically beneficial outcomes.
VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence
In contrast to previous methods that rely on dense correspondences, we introduce the VideoSwap framework that exploits semantic point correspondences, inspired by our observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape.
Disambiguation of morpho-syntactic features of African American English -- the case of habitual be
To overcome the scarcity, we employ a combination of rule-based filters and data augmentation that generate a corpus balanced between habitual and non-habitual instances.
Distribution of Si II $λ$6355 Velocities of Type Ia Supernovae and Implications for Asymmetric Explosions
In the two cases we consider, 35\% of SNe Ia are considered to be asymmetric in Case 1, and all SNe Ia are asymmetric in Case 2.
High Energy Astrophysical Phenomena Cosmology and Nongalactic Astrophysics
Prosody leaks into the memories of words
Extending this interpretation, these results suggest that predictability is closely linked to prosodic prominence, and that the lexical representation of a word includes phonetic details associated with its average prosodic prominence in discourse.
CDeepEx: Contrastive Deep Explanations
The second question asks, "Why did you not choose answer B over A?"
Dense Captioning with Joint Inference and Visual Context
The goal is to densely detect visual concepts (e. g., objects, object parts, and interactions between them) from images, labeling each with a short descriptive phrase.
Improving Image Classification with Location Context
With the widespread availability of cellphones and cameras that have GPS capabilities, it is common for images being uploaded to the Internet today to have GPS coordinates associated with them.
Learning Temporal Embeddings for Complex Video Analysis
In this paper, we propose to learn temporal embeddings of video frames for complex video analysis.
Co-localization in Real-World Images
In this paper, we tackle the problem of co-localization in real-world images.
Discriminative Segment Annotation in Weakly Labeled Video
Second, we ensure that CRANE is robust to label noise, both in terms of tagged videos that fail to contain the concept as well as occasional negative videos that do.
Shifting Weights: Adapting Object Detectors from Image to Video
In this paper, we tackle the problem of adapting object detectors learned from images to work well on videos.
