Kunjal Panchal

Kunjal Panchal, Saayan Mitra, Somdeb Sarkhel et al.

Recent advances in video-language models have enabled powerful applications like video retrieval, captioning, and assembly. However, executing such multi-stage pipelines efficiently on mobile devices remains challenging due to redundant model loads and fragmented execution. We introduce Atom, an on-device system that restructures video-language pipelines for fast and efficient execution. Atom decomposes a billion-parameter model into reusable modules, such as the visual encoder and language decoder, and reuses them across subtasks like captioning, reasoning, and indexing. This reuse-centric design eliminates repeated model loading and enables parallel execution, reducing end-to-end latency without sacrificing performance. On commodity smartphones, Atom achieves 27--33% faster execution compared to non-reuse baselines, with only marginal performance drop ($\leq$ 2.3 Recall@1 in retrieval, $\leq$ 1.5 CIDEr in captioning). These results position Atom as a practical, scalable approach for efficient video-language understanding on edge devices.

Kunjal Panchal

In vision and linguistics; the main input modalities are facial expressions, speech patterns, and the words uttered. The issue with analysis of any one mode of expression (Visual, Verbal or Vocal) is that lot of contextual information can get lost. This asks researchers to inspect multiple modalities to get a thorough understanding of the cross-modal dependencies and temporal context of the situation to analyze the expression. This work attempts at preserving the long-range dependencies within and across different modalities, which would be bottle-necked by the use of recurrent networks and adds the concept of delta-attention to focus on local differences per modality to capture the idiosyncrasy of different people. We explore a cross-attention fusion technique to get the global view of the emotion expressed through these delta-self-attended modalities, in order to fuse all the local nuances and global context together. The addition of attention is new to the multi-modal fusion field and currently being scrutinized for on what stage the attention mechanism should be used, this work achieves competitive accuracy for overall and per-class classification which is close to the current state-of-the-art with almost half number of parameters.

Kunjal Panchal

This project implements the paper "Video Textures" by Szeliski. The aim is to create a "Moving Picture" or as we popularly call it, a GIF; which is "somewhere between a photograph and a video". The idea is to input a video which has some repeated motion (the texture), such as a flag waving, rain, or a candle flame. The output is a new video that infinitely extends the original video in a seamless way. In practice, the output isn't really infinte, but is instead looped using a video player and is sufficiently long as to appear to never repeat. Our goal from this implementation was to: improve distance metric by switching from a crude sum of squared distance to most sophisticated wavelet-based distance; add intensity normalization, cross-fading and morphing to the suggested basic algorithm. We also experiment on the trade-off between variety and smoothness.

Kunjal Panchal

Honey Encryption is an approach to encrypt the messages using low min-entropy keys, such as weak passwords, OTPs, PINs, credit card numbers. The ciphertext is produces, when decrypted with any number of incorrect keys, produces plausible-looking but bogus plaintext called "honey messages". But the current techniques used in producing the decoy plaintexts do not model human language entirely. A gibberish, random assortment of words is not enough to fool an attacker; that will not be acceptable and convincing, whether or not the attacker knows some information of the genuine source. In this paper, I focus on the plaintexts which are some non-numeric informative messages. In order to fool the attacker into believing that the decoy message can actually be from a certain source, we need to capture the empirical and contextual properties of the language. That is, there should be no linguistic difference between real and fake message, without revealing the structure of the real message. I employ natural language processing and generalized differential privacy to solve this problem. Mainly I focus on machine learning methods like keyword extraction, context classification, bags-of-words, word embeddings, transformers for text processing to model privacy for text documents. Then I prove the security of this approach with e-differential privacy.