Akshita Gupta

Akshita Gupta, Tatiana Likhomanenko, Karren Dai Yang et al.

The rapid progress of foundation models and large language models (LLMs) has fueled significantly improvement in the capabilities of machine learning systems that benefit from mutlimodal input data. However, existing multimodal models are predominantly built on top of pre-trained LLMs, which can limit accurate modeling of temporal dependencies across other modalities and thus limit the model's ability to jointly process and leverage multimodal inputs. To specifically investigate the alignment of text, video, and speech modalities in LLM-style (decoder-only) models, we consider a simplified multimodal generation task, Video-Text to Speech (VTTS): speech generation conditioned on both its corresponding text and video of talking people. The ultimate goal is to generate speech that not only follows the text but also aligns temporally with the video and is consistent with the facial expressions. In this paper, we first introduce Visatronic, a unified multimodal decoder-only transformer model that adopts an LLM-style architecture to embed visual, textual, and speech inputs into a shared subspace, treating all modalities as temporally aligned token streams. Next, we carefully explore different token mixing strategies to understand the best way to propagate information from the steps where video and text conditioning is input to the steps where the audio is generated. We extensively evaluate Visatronic on the challenging VoxCeleb2 dataset and demonstrate zero-shot generalization to LRS3, where Visatronic, trained on VoxCeleb2, achieves a 4.5% WER, outperforming prior SOTA methods trained only on LRS3, which report a 21.4% WER. Additionally, we propose a new objective metric, TimeSync, specifically designed to measure phoneme-level temporal alignment between generated and reference speech, further ensuring synchronization quality. Demo: https://apple.github.io/visatronic-demo/

Akshita Gupta, Gaurav Mittal, Ahmed Magooda et al.

Temporal Action Localization (TAL) involves localizing and classifying action snippets in an untrimmed video. The emergence of large video foundation models has led RGB-only video backbones to outperform previous methods needing both RGB and optical flow modalities. Leveraging these large models is often limited to training only the TAL head due to the prohibitively large GPU memory required to adapt the video backbone for TAL. To overcome this limitation, we introduce LoSA, the first memory-and-parameter-efficient backbone adapter designed specifically for TAL to handle untrimmed videos. LoSA specializes for TAL by introducing Long-Short-range Adapters that adapt the intermediate layers of the video backbone over different temporal ranges. These adapters run parallel to the video backbone to significantly reduce memory footprint. LoSA also includes Long-Short-range Gated Fusion that strategically combines the output of these adapters from the video backbone layers to enhance the video features provided to the TAL head. Experiments show that LoSA significantly outperforms all existing methods on standard TAL benchmarks, THUMOS-14 and ActivityNet-v1.3, by scaling end-to-end backbone adaptation to billion-parameter-plus models like VideoMAEv2~(ViT-g) and leveraging them beyond head-only transfer learning.

Johanna Orsholm, John Quinto, Hannu Autto et al.

Insects comprise millions of species, many experiencing severe population declines under environmental and habitat changes. High-throughput approaches are crucial for accelerating our understanding of insect diversity, with DNA barcoding and high-resolution imaging showing strong potential for automatic taxonomic classification. However, most image-based approaches rely on individual specimen data, unlike the unsorted bulk samples collected in large-scale ecological surveys. We present the Mixed Arthropod Sample Segmentation and Identification (MassID45) dataset for training automatic classifiers of bulk insect samples. It uniquely combines molecular and imaging data at both the unsorted sample level and the full set of individual specimens. Human annotators, supported by an AI-assisted tool, performed two tasks on bulk images: creating segmentation masks around each individual arthropod and assigning taxonomic labels to over 17 000 specimens. Combining the taxonomic resolution of DNA barcodes with precise abundance estimates of bulk images holds great potential for rapid, large-scale characterization of insect communities. This dataset pushes the boundaries of tiny object detection and instance segmentation, fostering innovation in both ecological and machine learning research.

Akshita Gupta, Aditya Arora, Sanath Narayan et al.

Open-Vocabulary Temporal Action Localization (OVTAL) enables a model to recognize any desired action category in videos without the need to explicitly curate training data for all categories. However, this flexibility poses significant challenges, as the model must recognize not only the action categories seen during training but also novel categories specified at inference. Unlike standard temporal action localization, where training and test categories are predetermined, OVTAL requires understanding contextual cues that reveal the semantics of novel categories. To address these challenges, we introduce OVFormer, a novel open-vocabulary framework extending ActionFormer with three key contributions. First, we employ task-specific prompts as input to a large language model to obtain rich class-specific descriptions for action categories. Second, we introduce a cross-attention mechanism to learn the alignment between class representations and frame-level video features, facilitating the multimodal guided features. Third, we propose a two-stage training strategy which includes training with a larger vocabulary dataset and finetuning to downstream data to generalize to novel categories. OVFormer extends existing TAL methods to open-vocabulary settings. Comprehensive evaluations on the THUMOS14 and ActivityNet-1.3 benchmarks demonstrate the effectiveness of our method. Code and pretrained models will be publicly released.