@sreeb.bsky.social
PhD student @PennState • Multimodal Learning x Affective Computing • ex-Microsoft
We also conduct a fine-grained error analysis and show that the underlying ground truth data in popular emotion datasets is inherently unreliable, adding to the challenges of this highly subjective task! Check out the preprint for more details! 🧐
February 22, 2025 at 7:55 PM
We also conduct a fine-grained error analysis and show that the underlying ground truth data in popular emotion datasets is inherently unreliable, adding to the challenges of this highly subjective task! Check out the preprint for more details! 🧐
We show that: 1️⃣ foundation models lag behind architectures designed specifically for emotion recognition, 2️⃣ show biases towards specific emotions and response formats, and 3️⃣ fail at predicting emotions under assumed personas.
February 22, 2025 at 7:55 PM
We show that: 1️⃣ foundation models lag behind architectures designed specifically for emotion recognition, 2️⃣ show biases towards specific emotions and response formats, and 3️⃣ fail at predicting emotions under assumed personas.
The Worlds I See - Dr. Fei-Fei Li’s autobiography.
December 19, 2024 at 3:07 AM
The Worlds I See - Dr. Fei-Fei Li’s autobiography.
Will be eagerly looking forward to your course nonetheless!
December 4, 2024 at 10:38 PM
Will be eagerly looking forward to your course nonetheless!
And can such representations be compounded?
In the context of multimodal foundation models, can we create models that can process such composite entities as a single modality of input?
Not sure if this is too naive an idea or more of an engineering than a research problem 😅
In the context of multimodal foundation models, can we create models that can process such composite entities as a single modality of input?
Not sure if this is too naive an idea or more of an engineering than a research problem 😅
December 4, 2024 at 10:37 PM
And can such representations be compounded?
In the context of multimodal foundation models, can we create models that can process such composite entities as a single modality of input?
Not sure if this is too naive an idea or more of an engineering than a research problem 😅
In the context of multimodal foundation models, can we create models that can process such composite entities as a single modality of input?
Not sure if this is too naive an idea or more of an engineering than a research problem 😅
The possibilities of what a “modality” can be is endless. Considering composite entities (like a user or a complete human), can we say that a single representation of a complex entity is as good as/better/worse than some combination of its subparts (language/speech by the human, appearance, etc.)?
December 4, 2024 at 10:35 PM
The possibilities of what a “modality” can be is endless. Considering composite entities (like a user or a complete human), can we say that a single representation of a complex entity is as good as/better/worse than some combination of its subparts (language/speech by the human, appearance, etc.)?